• MALSORI
• /
• no.60
• /
• pp.165-180
• /
• 2006

In this paper, we present several confidence measures (CM) for speech recognition systems to evaluate the reliability of recognition results. We propose heuristic CMs such as mean log-likelihood score, N-best word log-likelihood ratio, likelihood sequence fluctuation and likelihood ratio testing(LRT)-based CMs using several types of anti-models. Furthermore, we propose new algorithms to add weighting terms on phone-level log-likelihood ratio to merge word-level log-likelihood ratios. These weighting terms are computed from the distance between acoustic models and knowledge-based phoneme classifications. LRT-based CMs show better performance than heuristic CMs excessively, and LRT-based CMs using phonetic information show that the relative reduction in equal error rate ranges between $8{\sim}13%$ compared to the baseline LRT-based CMs. We use the support vector machine to fuse several CMs and improve the performance of utterance verification. From our experiments, we know that selection of CMs with low correlation is more effective than CMs with high correlation.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.10a
• /
• pp.96-100
• /
• 1996

So far the analysis and modeling of cutting process is studied commonly assumed as being linear stochastic or chaotic without experimental verification. So we verified force signals of cutting process(ball end-milling) is low-dimensional chaos by calculating Lyapunov Exponents. reconstructing attractor using time delay coordinates and calcula-ting it's fractal dimension.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.12
• /
• pp.34-41
• /
• 2003

This paper suggests a methodology fur improving the machining accuracy by compensating for the machining errors based on on-machine measurement process. Probing errors and machine tool errors included in the measurement data were calibrated or compensated to obtain the actual machining errors. Machine tool errors were modeled in forward and backward directions according to the axis movement direction to consider the effects of backlash errors on the measurement data, and model parameters were determined by measuring a cube array artifact. A rectangular workpiece was machined and then measured with a touch probe as a verification experiment. Machining experiments showed that the machining errors were reduced to within the designated tolerance after compensating for the actual machining errors by modifying the original footpath for the next-step machining.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.358-362
• /
• 2004

Verification and testing are complementary techniques that are used to increase the level of confidence in the correct functioning of communication systems as prescribed by their specifications. This paper presents an experience of model checking for a formal railway signaling protocol specified in LTS (Labeled Transition System). This formal approach checks deadlock, livelock and reachability for the state and action to verify whether properties expressed in modal logic are true on specifications. We also propose a formal method for semi-automated test case generation for a railway signaling protocol described in I/O FSM (Input/Output Finite State Machine). This enables the generation of more complete and consistent test sequence for conformance testing. The above functions are implemented by C++ language and included within RSPVTE (Railway Signaling Protocol Verification and Testing Environment).

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.453-454
• /
• 2006

This paper describes a processing verification technique for developing about end-milling cutters. Developed software is processing verification module for manufacturing. By using cutting simulation method, we can obtain center points of finding wheel via Boolean operation between a grinding wheel and a cylindrical workpiece. The obtained CL data can be used for calculating NC data. After then, we can simulate by using designed grinding machine and NC data. This research has been implemented on a commercial CAD system by using the API function programming. The operator can evaluate the cutting simulation process and reduce the time of design and manufacturing.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1581-1584
• /
• 2003

This paper proposed efficient manufacturing system using OMM(on-machine measurement) system and OMM operating S/W based 3D modeler. A Developed program connected tool machine with RS232C. It is composed two operating system that touch probe operating and laser displacement sensor operating system. A program for touch probe possible measure considered inspection feature and CAD data. The laser operating program is used inspection for profile. very small hole using installed feature data. This system is applied manufacturing line of mold(cavity, core) also verification of efficiency manufacturing process that production, reduction machining error of each process

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.337-341
• /
• 2002

In these day, micro systems have gained attention with development of advance technologies. Researches about the fabrication of micro parts are actively made in the whole world. Among the researches, technology for micro injection molding machine is one of the key issues for fabrication of micro parts. In this study, we developed a micro injection molding machine for micro parts. To achieve this, injection unit was constructed using a screw with diameter of 12 mm. Clamping unit with clamping force of 1.75 kgf/$\textrm{cm}^2$ was constructed. Also verification test fur fabrication of micro parts was performed. It was performed that the micro injection molding machine can fabricate micro parts based on the result.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.419-427
• /
• 2023

In this study, optimal adhesion conditions to alleviate defects caused by heat shrinkage with FDM type 3D printers with machine learning are researched. Machine learning is one of the "statistical methods of extracting the law from data" and can be classified as supervised learning, unsupervised learning and reinforcement learning. Among them, a function model for adhesion between the bed and the output is presented using supervised learning specialized for optimization, which can be expected to reduce output defects with FDM type 3D printers by deriving conditions for optimum adhesion between the bed and the output. Machine learning codes prepared using Python generate a function model that predicts the effect of operating variables on adhesion using data obtained through adhesion testing. The adhesion prediction data and verification data have been shown to be very consistent, and the potential of this method is explained by conclusions.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.3 no.4
• /
• pp.428-432
• /
• 2014

Rotating machines are an integral part of large electrical power machinery in most of the industries. Any degradation or outages in the rotating electric machinery can result in significant losses in productivity. It is critical to monitor the equipment for any degradation's so that it can serve as an early warning for adequate maintenance activities and repair. Prior research and field studies have indicated that the rotating machines have a particular type of signal structure during the initial start-up transient. A machine performance can be studied based on the effect of degradation in signal parameters. In this paper a data-acquisition system and the FFT algorithm has been design and model using the MATLAB and Simulink. The implementation had been carried out on the TMS320 DSP Processor and various testing and verification of the machine performance had been carried out. The results show good agreement with expected results for both simulated and real-time data. The real-time data from AC water pumps which have rotating motors built-in were collected and analysed. The FFT algorithm provides frequency response and based on this frequency response performance of the machine had been measured.The FFT algorithm provides only approximation about the machine performances.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.648-659
• /
• 2024

Author verification is challenging because of the diversity in writing styles. We propose an enhanced handwriting verification method that combines handcrafted and automatically extracted features. The method uses a genetic algorithm to reduce the dimensionality of the feature set. We consider offline Bangla handwriting content and evaluate the proposed method using handcrafted features with a simple logistic regression, radial basis function network, and sequential minimal optimization as well as automatically extracted features using a convolutional neural network. The handcrafted features outperform the automatically extracted ones, achieving an average verification accuracy of 94.54% for 100 writers. The handcrafted features include Radon transform, histogram of oriented gradients, local phase quantization, and local binary patterns from interwriter and intrawriter content. The genetic algorithm reduces the feature dimensionality and selects salient features using a support vector machine. The top five experimental results are obtained from the optimal feature set selected using a consensus strategy. Comparisons with other methods and features confirm the satisfactory results.