• Korean Journal of Occupational Health Nursing
• /
• v.10 no.2
• /
• pp.174-182
• /
• 2001

This study was performed to find out the differences between noise levels of hospital wards and the nurses efforts for noise management in some general hospitals. The hospital wards selected were the intensive care unit(ICU), the emergency room(ER), the nursery room(NR), the internal medicine(IM), the general surgery(GS) among the 5 general hospitals located in Seoul. The data were collected from August 3 to September 13, 1999 through questionnaire survey and noise measurement in each nursing station of hospital wards. Data analysis was done by SPSS 8.0 package among the 305 questionnaires and 24 hours monitored noise levels. Frequency, Chi-square and ANOVA test were used. The study results were as belows: 1. The noise level measured by 24 hours monitoring survey were exceeded on the standard limit in all the hospital wards. Data also showed that noise levels were significantly different in each ward among the three shifts working duties. 2. The subjects were all female nurses. They were mostly working in the ICU ward(28.9%). They were 26~30 years old (43.9%), junior college graduates(57.0%), working for 1~5 years(55.1%) as staff-nurse(85.6%). There were no significant differences between hospital wards and general characteristics of nurses. 3. The noise levels perceived by nurses were regarded as 'Highly noisy'(56.4%), especially during the 11:30 and 15:30 (30.2%) o'clock. Data also showed that noise education was not ever given to nurses(89.9%). Nurses also responded that they hardly put an effort to reduce noise level(54.8%). However, there were significant differences between wards and noisy working time, experience of noise education and level of effort for noise reduction. 4. Nurses also perceived the ventilator alarm and EKG-alarm as the most disturbing sounds in the ICU, human voice and telephone ringing in the ER, human voice and EKG-alarming in the NR, human voices and telephone ringing in IM and GS both wards respectively in order. There were significant differences between hospital wards and noise making factors. 5. Nurses were shown that they regarded highly 'Sound reduction of the human voice', 'Careful handling on medical instruments', and 'Immediate appliances on alarming materials' as the practical method for noise management. There were significant differences between hospital wards and behavioral practical efforts for noise management. According to that results, the statistical differences were shown in the 24 hour monitored noise levels in each ward. Also, nurses perceived the noise severity differently and they approached variously on the practical efforts for noise reduction in each ward. Thus, author thinks that concrete and systematic endeavor will be necessary for noise reduction and management in hospitals for better working and healing environment for both of patients and staffs.

• MALSORI
• /
• no.53
• /
• pp.103-118
• /
• 2005

The performance of speech recognition system is degraded by mismatch between training and test environments. Recently, Stereo-based Piecewise LInear Compensation for Environments (SPLICE) was introduced to overcome environmental mismatch using stereo data. In this paper, we propose several methods to improve the conventional SPLICE and evaluate them in the Aurora2 task. We generalize SPLICE to compensate for covariance matrix as well as mean vector in the feature space, and thereby yielding the error rate reduction of 48.93%. We also employ the weighted sum of correction vectors using posterior probabilities of all Gaussians, and the error rate reduction of 48.62% is achieved. With the combination of the above two methods, the error rate is reduced by 49.61% from the Aurora2 baseline system.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.693-698
• /
• 2001

Noisy data are often fitted using a smoothing parameter, controlling the importance of two objectives that are opposite to a certain extent. One of these two is smoothness and the other is closeness to the input data. The optimal value of this parameter minimizes the error of the result. This optimum cannot be found exactly, simply because the exact data are unknown. This paper propose the threshold value for noise reduction based on wavelet-thresholding. In the proposed method PSNR results show that the threshold value performs excellently in comparison with conventional methods without knowing the noise variance and volume of signal.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.5
• /
• pp.227-234
• /
• 2020

In this paper, we propose wav-U-Net to improve speech enhancement in heavy noisy environments, and it has implemented three principal techniques. First, as input data, we use 128 modified Mel-scale filter banks which can reduce computational burden instead of 512 frequency bins. Mel-scale aims to mimic the non-linear human ear perception of sound by being more discriminative at lower frequencies and less discriminative at higher frequencies. Therefore, Mel-scale is the suitable feature considering both performance and computing power because our proposed network focuses on speech signals. Second, we add a simple ResNet as pre-processing that helps our proposed network make estimated speech signals clear and suppress high-frequency noises. Finally, the proposed U-Net model shows significant performance regardless of the kinds of noise. Especially, despite using a single channel, we confirmed that it can well deal with non-stationary noises whose frequency properties are dynamically changed, and it is possible to estimate speech signals from noisy speech signals even in extremely noisy environments where noises are much lauder than speech (less than SNR 0dB). The performance on our proposed wav-U-Net was improved by about 200% on SDR and 460% on NSDR compared to the conventional Jansson's wav-U-Net. Also, it was confirmed that the processing time of out wav-U-Net with 128 modified Mel-scale filter banks was about 2.7 times faster than the common wav-U-Net with 512 frequency bins as input values.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.6
• /
• pp.566-571
• /
• 2009

This paper proposes noise-robust fast speaker adaptation method based on the eigenvoice framework in various noisy environments. The proposed method is focused on de-noising and environment clustering. Since the de-noised adaptation DB still has residual noise in itself, environment clustering divides the noisy adaptation data into similar environments by a clustering method using the cepstral mean of non-speech segments as a feature vector. Then each adaptation data in the same cluster is used to build an environment-clustered speaker adapted (SA) model. After selecting multiple environmentally clustered SA models which are similar to test environment, the speaker adaptation based on an appropriate linear combination of clustered SA models is conducted. According to our experiments, we observe that the proposed method provides error rate reduction of $40{\sim}59%$ over baseline with speaker independent model.

• The Korean Journal of Applied Statistics
• /
• v.36 no.6
• /
• pp.501-514
• /
• 2023

When analyzing high dimensional data such as text data, if we input all the variables as explanatory variables, statistical learning procedures may suffer from over-fitting problems. Furthermore, computational efficiency can deteriorate with a large number of variables. Dimensionality reduction techniques such as feature selection or feature extraction are useful for dealing with these problems. The sparse principal component analysis (SPCA) is one of the regularized least squares methods which employs an elastic net-type objective function. The SPCA can be used to remove insignificant principal components and identify important variables from noisy observations. In this study, we propose a dimension reduction procedure for text data based on the SPCA. Applying the proposed procedure to real data, we find that the reduced feature set maintains sufficient information in text data while the size of the feature set is reduced by removing redundant variables. As a result, the proposed procedure can improve classification accuracy and computational efficiency, especially for some classifiers such as the k-nearest neighbors algorithm.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.17 no.1
• /
• pp.23-30
• /
• 1980

The reconstruction problem in a low dose case requires some compromise of resolution and noise artifacts, and also some modification of filter kernels depending on the signal-to-noise ratio of projection data. In this paper, ail algorithm for the reconstruction of an image function from noisy projection data is suggested, based on minimum-mean-square error criterion. Modification of the falter kernel is made from information (statistics) obtained from the projection data. The simulation study Proves that this algorithm, based on the Wiener falter approach, provides substantially improved image with reduction of noise as well as improvement of the resolution. An approximate method was also studied which leads to the possible use of a recursive filter in the convolution process of image reconstruction.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.129-136
• /
• 2005

To reduce the noise in the noisy speech, it is desirable to change the parameters of the speech processing system according to the noise intensity to reproduce a good quality speech. This paper proposes an estimation method of noise intensity using a three layered neural network, which is able to learn the three graded speeches that is degraded by white noise or road noise. Experimental results demonstrate that the noise intensity could be estimated by the neural network. Even if the speakers and speech data are different from the training data, estimation rates for the noise intensity can be estimated by the neural network with an average accuracy of $95\%$ or more for white noise.

• Structural Engineering and Mechanics
• /
• v.83 no.4
• /
• pp.537-549
• /
• 2022

In this paper, a novel multi-feature model predictive control (MPC) framework with real-time and adaptive performances is proposed for intelligent structural control in which some drawbacks of the algorithm including, complex control rule and non-optimality, are alleviated. Hence, Linear Programming (LP) is utilized to simplify the resulted control rule. Afterward, the Whale Optimization Algorithm (WOA) is applied to the optimal and adaptive tuning of the LP weights independently at each time step. The stochastic control rule is also achieved using Kalman Filter (KF) to handle noisy measurements. The Extreme Learning Machine (ELM) is then adopted to develop a data-driven and real-time control algorithm. The efficiency of the developed algorithm is then demonstrated by numerical simulation of a twenty-story high-rise benchmark building subjected to earthquake excitations. The competency of the proposed method is proven from the aspects of optimality, stochasticity, and adaptivity compared to the KF-based MPC (KMPC) and constrained MPC (CMPC) algorithms in vibration suppression of building structures. The average value for performance indices in the near-field and far-field (El earthquakes demonstrates a reduction up to 38.3% and 32.5% compared with KMPC and CMPC, respectively.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.109-123
• /
• 2004

Corporate financial distress and bankruptcy prediction is one of the major application areas of artificial neural networks (ANNs) in finance and management. ANNs have showed high prediction performance in this area, but sometimes are confronted with inconsistent and unpredictable performance for noisy data. In addition, it may not be possible to train ANN or the training task cannot be effectively carried out without data reduction when the amount of data is so large because training the large data set needs much processing time and additional costs of collecting data. Instance selection is one of popular methods for dimensionality reduction and is directly related to data reduction. Although some researchers have addressed the need for instance selection in instance-based learning algorithms, there is little research on instance selection for ANN. This study proposes a genetic algorithm (GA) approach to instance selection in ANN for bankruptcy prediction. In this study, we use ANN supported by the GA to optimize the connection weights between layers and select relevant instances. It is expected that the globally evolved weights mitigate the well-known limitations of gradient descent algorithm of backpropagation algorithm. In addition, genetically selected instances will shorten the learning time and enhance prediction performance. This study will compare the proposed model with other major data mining techniques. Experimental results show that the GA approach is a promising method for instance selection in ANN.