• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.485-492
• /
• 2017

GMM has been one of the most popular methods for scream sound detection. In the conventional GMM, the whole training data is divided into scream sound and non-scream sound, and the GMM is trained for each of them in the training process. Motivated by the idea that the process of scream sound detection is very similar to that of speaker recognition, the UBM which has been used quite successfully in speaker recognition, is proposed for use in scream sound detection in this study. We could find that UBM shows better performance than the traditional GMM from the experimental results.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.11
• /
• pp.1559-1563
• /
• 2014

Recently, the prevention of crime using CCTV draws special in accordance with the higher crime incidence rate. Therefore security systems like a CCTV with audio capability are developing for giving an instant alarm. This paper proposes a scream detecting engine from various ambient noises in real environment for surveillance systems. The proposed engine detects scream signals among the various ambient noises using the features extracted in time/frequency domain. The experimental result shows the performance of our engine is very promising in comparison with the traditional engines using the model based features like LPC, LPCC and MFCC. The proposed method has a low computational complexity by using FFT and cross correlation coefficients instead of extracting complex features like LPC, LPCC and MFCC. Therefore the proposed engine can be efficient for audio-based surveillance systems with low SNRs in real field.

• Korean Architects
• /
• s.510
• /
• pp.10-10
• /
• 2011

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.6
• /
• pp.804-809
• /
• 2014

Recently, the prevention of crime using CCTV draws special in accordance with the higher crime incidence rate. Therefore security systems like a CCTV with audio capability are developing for giving an instant alarm. This paper proposes an analysis on screams and ambient noises for security systems with audio capability. This analysis result will be helpful for security systems to detect screams well with various ambient noises in real environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.1
• /
• pp.29-40
• /
• 2005

In this paper we consider the security of recently proposed software-orienred stram cipher HELIX, SCREAM, MUGI, and PANAMA against algebraic attacks. Algebraic attack is a key recovery attack by solving an over-defined system of multi-variate equations with input-output pairs of an algorithm. The attack was firstly applied to block ciphers with some algebraic properties and then it has been mon usefully applied to stream ciphers. However it is difficult to obtain over-defined algebraic equations for a given cryptosystem in general. Here we analyze recently proposed software-oriented stream ciphers by constructing a system of equations for each cipher. furthermore we propose three design considerations of software-oriented stream ciphers.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.3 no.4
• /
• pp.286-292
• /
• 2011

In order to design a shear coaxial injector of solid particles for underwater propulsion system, basic experiments on gas-liquid shear coaxial injector are necessary. In the gas-liquid coaxial injector self-pulsation usually occurs with an intense scream. When self-pulsation occurs, mass flow rate oscillation and intense scream are detected by the interactions between the liquid and gas phase. Self-pulsation must be suppressed since this oscillation may cause combustion instabilities. Considerable research has been conducted on self-pulsation characteristics, but these researches are conducted in swirl coaxial injector. The main objective of this research is to understand the characteristics of self-pulsation in shear coaxial injector and reveal the mechanism of the phenomenon. Toward this object, self-pulsation frequency and spray patterns are measured by laser diagnostics and indirect photography. The self-pulsation characteristics of shear coaxial injector are studied with various injection conditions, such as the pressure drop of liquid and gas phase, and recess ratio. It was found that the frequency of the self-pulsation is proportional to the liquid and gas Reynolds number, and proportional to the L/d.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2004.03a
• /
• pp.228-233
• /
• 2004

The spray and acoustic characteristics by the self-oscillation of a swirl coaxial injector were experimentally studied. The self-oscillation of a swirl coaxial injector is defined as pressure and flowrate oscillations by a time-delayed feedback between liquid and gas phase and has strong influences on atomization and mixing processes. Hence the occurrence and effect of the self-oscillation are measured using shadow photography technique, acoustic test and PDPA. The occurrence of self-oscillation largely depends on the injection conditions, such as pressure drop of liquid phase and relative momentum ratio. From the experimental results, self-oscillation occurs when the momentum of gas phase is enough large and the smaller the pressure drop of liquid phase is, the better self-oscillation occurs at the same momentum ratio. The self-oscillation is also affected by injector geometries, increasing the recess length results in the expansion of self-oscillation region and the increase of sound pressure level. The self-oscillation of a swirl coaxial injector accompanies a high intensity scream and this scream may provide harmful disturbances to combustion processes. Self-oscillation leads to strong changes in the drop size distribution and smoothly varies the slope of radial SMD distribution.

• Journal of Practical Engineering Education
• /
• v.15 no.3
• /
• pp.605-614
• /
• 2023

In In the era of digital transition, AI-based personalized services are emerging in the field of education. This research aims to examine the development strategies for implementing AI-based learning services in school. Focusing on AI-based math learning service "Math Cell" developed by i-Scream Edu, this study surveyed the functional requirements from the perspective of an educator. The results were analyzed for importance and suitability using IPA, and expert opinions were surveyed to explore specific development directions for the service. Consequently, importance in all areas such as diagnosis, learning, evaluation, and management averaged 4.82 and performance averaged 4.56, showing excellent results in most questions, and in particular, importance was higher than performance. Among certain detailed functions, concept learning, customized task presentation, evaluation result analysis function, dashboard-related functions, and learning materials in the dashboard were not intuitive for students to understand and had to be supplemented. This study provides meaningful insights by summarizing expert opinions on AI-based personalized mathematics learning services, thereby contributing to the exploration of the development strategies for "Math Cell".

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.197-200
• /
• 2014

본 논문에서는 오디오기반 CCTV에서 비명 구간을 효과적으로 검출하기 위한 가중치 값을 실험을 통해 결정 하고자 한다. 경계값은 학습구간의 평균값에 가중치 값을 곱해주어 계산되며, 이 때 가중치 값에 의해 비명 구간 검출 성능이 결정된다. 따라서 본 논문에서는 가장 좋은 성능을 보이는 가중치 값을 결정하기 위해 가중치 값을 변화시키며 실험을 하였다. 그 결과 w값이 3일 때 검출률과 오인식률에서 가장 좋은 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1133-1136
• /
• 2017

폐쇄회로 텔레비전(CCTV, Closed Circuit Television)은 범죄 예방을 위해서 현재 많이 사용되고 있다. 하지만, CCTV의 경우 주로 영상에 기반하기 때문에 사각지대가 존재할 수 있으며 범죄 발생시 즉각적인 대처보다는 후속 조치에 주로 활용된다. 본 논문에서는 이와 같은 문제점을 해결하기 위해 비명을 탐지할 수 있는 치안 향상을 위한 비명 감지 시스템을 설계하고 구현하였다. 제안하는 시스템은 비명을 감지하면 경보음을 제공해주며, 중앙 시스템에 알림을 주어 관리자가 확인하고 즉각적인 대응이 가능할 수 있도록 할 수 있는 기능을 제공한다.