• MALSORI
• /
• no.49
• /
• pp.145-158
• /
• 2004

This paper is aiming at implementation of real-time speaker verification system using DSP board. Dialog/4, which is based on microprocessor and DSP processor, is selected to easily control telephone signals and to process audio/voice signals. Speaker verification system performs signal processing and feature extraction after receiving voice and its ID. Then through computing the likelihood ratio of claimed speaker model to the background model, it makes real-time decision on acceptance or rejection. For the verification experiments, total 15 speaker models and 6 background models are adopted. The experimental results show that verification accuracy rates are 99.5% for using telephone speech-based speaker models.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.1
• /
• pp.17-31
• /
• 2010

In VANET (Vehicular Ad hoc NETwork), vehicles can efficiently verify a large number of signatures efficiently using batch verification techniques. However, batch verification performed independently in each vehicle raises many redundant verification cost. Although, an RSU (Road Side Unit) can perform the batch verification as a proxy to reduce this cost, it additionally requires an efficient method to identify invalid signatures when the batch verification fails. In this paper, we analyze several ways of constructing a distributed batch verification system, and propose an efficient distributed batch verification system in which participating vehicles perform batch verification in a distributive manner for a small size signature set. In our proposed system, each node can report the batch verification result or the identified invalid signatures list and the RSU who received these reports can identify the invalid signatures and efficiently exclude them.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.115-123
• /
• 2021

Through machine learning-based load prediction, it is possible to prevent excessive power generation or unnecessary economic investment by estimating the appropriate amount of facility investment in consideration of the load that will increase in the future or providing basic data for policy establishment to distribute the maximum load. However, in order to secure the reliability of the developed load prediction model in the field, the performance comparison verification between the distribution line load prediction models must be preceded, but a comparative performance verification system between the distribution line load prediction models has not yet been established. As a result, it is not possible to accurately determine the performance excellence of the load prediction model because it is not possible to easily determine the likelihood between the load prediction models. In this paper, we developed a reliability verification system for load prediction models including a method of comparing and verifying the performance reliability between machine learning-based load prediction models that were not previously considered, verification process, and verification result visualization methods. Through the developed load prediction model reliability verification system, the objectivity of the load prediction model performance verification can be improved, and the field application utilization of an excellent load prediction model can be increased.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.34-40
• /
• 2000

In text-dependent speaker verification system, which text choice for speaker to utter is very important factor for performance improvement. In this paper, building a consonant mixture system using classification method of korean phonetic value is proposed. When it is applied to the web-based speaker verification system, it can cope with abrupt change of speaker's voice information and have the optimal performance in speaker verification system.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.185-187
• /
• 2005

The reactor protection system is the most important function for the safe operation of nuclear powerplants (NPPs) in that such system protects a nuclear reactor tore whose damage can cause an enormous disaster to the nuclear facility and the public. A digital reactor protection system (DRPS) is being developed in KAERI for use in the newly-constructed NPPs and also for replacing the existing analog-type reactor Protection systems. In this paper, an software verification and validation (V&V) activities for DRPS, which are independent of the DRPS development processes, are described according to the software development life cycle. The main activities of DRPS V&V processes are the software planning documentations, the verification of software requirements specification (SRS) and software design specification (SDS), the verification of codes, the tests of the integrated software and system. Moreover, the software safety analysis and the software configuration management are involved in the DRPS V&V processes. All of the V&V activities are described, in detail, in this paper.

• 시스템엔지니어링워크숍
• /
• s.6
• /
• pp.126-129
• /
• 2005

Systems engineering requirement verification model developmetn for High Speed Railway systems in progress is a national large system development program that is not only large-size and complex but also multi-disciplinary in nature. For the High Speed Railway TEP development, verification requirements that could verify system function, performance, and constraint, should be derived from SSS(system Segment specification). Hereafter, this could be referred to as verification requirements. System engineering process establishes traceability between verification requirements and system requirements. These tasks could be accomplished by the schema. using computer-aided Systems Engineering tool(CORE), High Speed Railway program can become a database and other system related to High Speed Railway program will be developed effectively and efficiently.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.2
• /
• pp.69-77
• /
• 2002

Speaker verification can be classified in two categories, text-dependent speaker verification and text-independent speaker verification. In this paper, we discuss text-dependent speaker verification. Text-dependent speaker verification system determines whether the sound characteristics of the speaker are equal to those of the specific person or not. In this paper we obtain the speaker data using a sound card in various noisy conditions, apply a new Hidden LMS (Least Mean Square) adaptive algorithm to it, and extract LPC (Linear Predictive Coding)-cepstrum coefficients as feature vectors. Finally, we use a competitive learning neural network for speaker verification. The proposed hidden LMS adaptive filter using a neural network reduces noise and enhances features in various noisy conditions. We construct a separate neural network for each speaker, which makes it unnecessary to train the whole network for a new added speaker and makes the system expansion easy. We experimentally prove that the proposed method improves the speaker verification performance.

• Journal of the Korea Safety Management & Science
• /
• v.17 no.1
• /
• pp.179-192
• /
• 2015

In an automated industry PLC plays a central role to control the automation system. Therefore, fault free operation of PLC controlled automation system is essential in order to maximize a firm's productivity. A prior test of control system is a practical way to check fault operations, but it is a time consuming job and can not check all possible fault operation. A formal verification of PLC program could be a best way to check all possible fault situation. Tracing the history of the study on formal verification, we found three problems, the first is that a formal representation of PLC control system is incomplete, the second is a state explosion problem and the third is that the verification result is difficult to use for the correction of control program. In this paper, we propose a transformation method to reproduce the control system correctly in formal model and efficient procedure to verify and correct the control program using verification result. To demonstrate the proposed method, we provided a suitable case study of an automation system.

• ETRI Journal
• /
• v.11 no.4
• /
• pp.22-36
• /
• 1989

In this paper, a design and implementation of an efficient protocol verification system named LOVE has been described. The LOVE has been developed specifically for LOTOS. It performs not only protocol syntax validation (PSV) but also protocol functional verification(PFV). The PSV is a test to check if a protocol is free from protocol syntax errors such as deadlocks and livelocks. The PFV confirms whether or not a protocol achieves its functional objectives. For the PSV, the reachability analysis is employed, and the observational equivalence test is used for the PFV. For protocol verification using the LOVE, a schematic protocol verification methodology has been outlined.

• Proceedings of the Safety Management and Science Conference
• /
• 2010.04a
• /
• pp.107-116
• /
• 2010

Government and company are unfolding greenhouse gas reduction activity to prevent the effects of global warming. Also, verification business through greenhouse gas inventory construction is spreaded variously. Greenhouse gas verification proceeds by document examination, risk analysis, field survey. Document investigates emission information, calculation standard, emission report, data management system. And through risk assessment result, establish field verification plan. Through study on risk assessment of greenhouse gas inventory verification, wish to reduce risk of verification.