• MALSORI
• /
• no.59
• /
• pp.27-51
• /
• 2006

For speech recognition systems, rejection function as well as decoding function is necessary to improve the reliability. There have been many research efforts on out-of-vocabulary word rejection, however, little attention has been paid on non-target sentence rejection. Recently pronunciation approaches using speech recognition increase the need for non-target sentence rejection to provide more accurate and robust results. In this paper, we proposed filler model method and word/phoneme detection ratio method to implement non-target sentence rejection system. We made performance evaluation of filler model along to word-level, phoneme-level, and sentence-level filler models respectively. We also perform the similar experiment using word-level and phoneme-level word/phoneme detection ratio method. For the performance evaluation, the minimized average of FAR and FRR is used for comparing the effectiveness of each method along with the number of words of given sentences. From the experimental results, we got to know that word-level method outperforms the other methods, and word-level filler mode shows slightly better results than that of word detection ratio method.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.3
• /
• pp.52-58
• /
• 2002

The purpose of condition monitoring and fault diagnosis is to detect faults occurring in machinery in order to improve the level of safety in plants and reduce operational and maintenance costs. The recognition performance is important not only to gain a high recognition rate bur a1so to minimize the diagnosis failures error rate by using off effective rejection module. We examined the problem of performance evaluation for the rejection scheme considering the accuracy of individual c1asses in order to increase the recognition performance. We use the Smith's method among the previous studies related to rejection method. Nearest neighbor classifier is used for classifying the machine conditions from the vibration signals. The experiment results for the performance evaluation of rejection show the modified optimum rejection method is superior to others.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.56-58
• /
• 2013

In this paper, a design method to obtain a band rejection characteristic in the 2.4-2.484 GHz WLAN band is studied for a series-fed dipole pair (SDP) antenna operating in the band of 1.7-2.7 GHz for mobile communication base station applications. The band rejection characteristic is achieved by inserting U-shaped slots on the coplanar strip line connecting the two dipole elements of the SDP antenna. The effects of the location and dimension of the slots on the band rejection characteristics are examined. The optimized SDP antenna with WLAN band rejection is fabricated on an FR4 substrate and the experimental results show that the antenna has a desired band rejection performance with a frequency band of 1.65-2.78 GHz (51.0%) for a VSWR < 2, and a rejection band of 2.39-2.54 GHz.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.262-267
• /
• 2004

This paper is concerned with a design method of two-degree-of-freedom controller by Coefficient Diagram Method (CDM). The two-degree-of-freedom control system satisfies both of tracking and disturbance rejection performances, but requires tuning of many parameters. By the proposed design method, these parameters can be obtained properly without any adjustment. Furthermore, the tracking and disturbance rejection performances can be simultaneously designed. The effectiveness of the proposed method is demonstrated by the simulation.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.637-645
• /
• 2015

Common-mode noise (CMN) is an unresolved problem in wireless capsule endoscopy (WCE) systems. In a WCE system, CMN originates from various electric currents found within the human body or external interference sources and causes critical demodulation performance degradation. The differential operation, a typical method for the removal of CMN rejection, can remove CMN by subtracting two signals simultaneously received by two reception sensors attached to a human body. However, when there is impedance mismatching between the two reception sensors, the differential operation method cannot completely remove CMN. Therefore, to overcome this problem, we propose an enhanced CMN rejection method. The proposed method performs not only subtraction but also addition between two received signals. Then a CMN ratio can be estimated by sufficient accumulation of division operation outcomes between the subtraction and addition outputs during the guard period. Finally, we can reject the residual CMN by combining the subtraction and addition outputs.

• Journal of Chest Surgery
• /
• v.36 no.6
• /
• pp.379-383
• /
• 2003

Background: An accurate diagnosis of the severity of the rejection after a heart transplantation relies on endomyo-cardial biopsy, but because of its invasiveness and the need for repeated examination makes it is an inappropriate monitoring method. Therefore, we have tried to find a monitoring method that is continuous and less invasive. Material and Method: Heterotopic heart transplantation using Ono-Lindsey Method was done in 20 rats, and then $^{99m}$ Tc-Pyrophosphate (PYP) scan was done after a month, Uptake ratio of transplanted heart to vertebrae (H/V) was obtained to be compared with the biopsy result. Result: Rejection was defined when the H/V uptake ratio was higher than 0.09, and we compared the uptake ratio with the results of biopsy. The result was true positives was 3, true negatives 12, false negatives 2, andfalse positives 3. Therefore sensitivity was 60% and specificity was 80%, diagnostic value was 75%. Conclusion: $^{99m}$Tc-Pyrophosphate (PYP) scan was a useful method for the evaluation of the heart transplantation rejection and it will be helpful for monitoring rejection as an non-invasive and simple method.hod.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.369-372
• /
• 2000

ESO(Evolutionary Structural Optimization) method is known that elements involved low stress value are removed from the previous model or that elements are added around elements involved high stress level on it and then the optimized model is obtained with required weight. Rejection ratio/addition ratio and evolutionary ratio are predefined and elements having lower/higher stress than reference stress, which average Mises stress on edge elements times rejection ratio, are deleted/added. In this study, when the plate having a cutout is subjected various in-plane load, a cutout shape is optimized using ESO method. ANSYS is used to analyse a finite element model and optimization procedure is made by APDL (ANSYS Parametric Design Language). ESO method is useful in rather than a complex structure optimization as well as a cutout shape optimization.

• Food Science and Biotechnology
• /
• v.17 no.5
• /
• pp.1066-1073
• /
• 2008

Sensitivity to 6-n-propylthiouracil (PROP) tasting predicts sensitivity to food qualities as well as rejection of some strong tasting foods. Using consumer rejection threshold (CRT) method, this study aimed to assess whether systematic changes in the taste intensities of familiar foods would lead to earlier rejection of these products by PROP tasters than by PROP non-tasters. Subjects rated the intensity of PROP solution and were divided into tasters (Ts) and non-tasters (NTs). And Ts were further divided into medium-tasters (MTs) and super-tasters (STs). Difference thresholds and CRTs were then evaluated for caffeine in coffee, citric acid in orange juice, and for NaCl in beef soup. For each food, Ts were more sensitive to variations in tastants than NTs. Ts also rejected more bitter coffee, more sour orange juice, and less salty beef soup more readily than did NTs. Comparisons among NTs, MTs, and STs gave fewer clear differences.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.43-48
• /
• 2012

This paper presents an iterative single-frequency continuous-wave signal-based I/Q regeneration method for improving image-rejection performance of multi-port junction-based direct receivers (MPDRs). This paper analyzes I/Q regeneration in MPDRs as I/Q mismatch compensation for direct conversion receivers. Based on the analysis, this paper evaluates the accuracy of I/Q regeneration in terms of the image-rejection ratio (IRR). The proposed method improves the IRR performance more than 20 dB compared to existing I/Q regeneration methods. Simulation results show that MPDRs using the proposed method can achieve an IRR of more than 70 dB, and that the bit error rate performances are almost the same as those of conventional coherent demodulators, even in fading channels.

• Phonetics and Speech Sciences
• /
• v.3 no.2
• /
• pp.65-70
• /
• 2011

Recently, audio-visual speech recognition (AVSR) has been studied to cope with noise problems in speech recognition. In this paper we propose a novel method of deciding weighting factors for audio-visual information fusion. We adopt the particle swarm optimization (PSO) to weighting factor determination. The AVSR experiments show that PSO-based normalized confidence measures (NCM) improve the rejection performance of mis-recognized words by 33%.