A speaker recognition system based on joint factor analysis (JFA) is proposed to improve whispering speakers’ recognition rate under channel mismatch. The system estimated separately the eigenvoice and the eigenchannel before calculating the corresponding speaker and the channel factors. Finally, a channel-free speaker model was built to describe accurately a speaker using model compensation. The test results from the whispered speech databases obtained under eight different channels showed that the correct recognition rate of a recognition system based on JFA was higher than that of the Gaussian Mixture Model-Universal Background Model. In particular, the recognition rate in cellphone channel tests increased significantly.
In the study, environmetric methods were successfully performed a) to explore natural and anthropogenic controls on reservoir water quality, b) to investigate spatial and temporal differences in quality, and c) to determine quality variables discriminating three reservoirs in Izmir, Turkey. Results showed that overall water quality was mainly governed by “natural factors” in the whole region. A parameter that was the most important in contributing to water quality variation for one reservoir was not important for another. Between summer and winter periods, difference in arsenic concentrations were statistically significant in the Tahtalı, Ürkmez and iron concentrations were in the Balçova reservoirs. Observation of high/low levels in two seasons was explained by different processes as for instance, dilution from runoff at times of high flow seeped through soil and entered the river along with the rainwater run-off and adsorption. Three variables “boron, arsenic and sulphate” discriminated quality among Balçova & Tahtalı, Balçova & Ürkmez and two variables “zinc and arsenic” among the Tahtalı & Ürkmez reservoirs. The results illustrated the usefulness of multivariate statistical techniques to fingerprint pollution sources and investigate temporal/spatial variations in water quality.
The aim of this article is to evaluate the quality of the Danube River in its course through Serbia as well as to demonstrate the possibilities for using three statistical methods: Principal Component Analysis (PCA), Factor Analysis (FA) and Cluster Analysis (CA) in the surface water quality management. Given that the Danube is an important trans-boundary river, thorough water quality monitoring by sampling at different distances during shorter and longer periods of time is not only ecological, but also a political issue. Monitoring was carried out at monthly intervals from January to December 2011, at 17 sampling sites. The obtained data set was treated by multivariate techniques in order, firstly, to identify the similarities and differences between sampling periods and locations, secondly, to recognize variables that affect the temporal and spatial water quality changes and thirdly, to present the anthropogenic impact on water quality parameters.
In the study suitability of water quality index approach and environmetric methods in fi ngerprinting heavy metal pollution as well as comparison of spatial variability of multiple contaminants in surface water were assessed in the case of The Gediz River Basin, Turkey. Water quality variables were categorized into two classes using factor and cluster analysis. Furthermore, soil contamination index was adapted to water pollution index and used to fi nd out the relative relationship between the reference standards and the current situation of heavy metal contamination in water. Results revealed that surface water heavy metal content was mainly governed by metal processing, textile and tannery industries in the region. On the other hand, metal processing industry discharges mainly degraded quality of water in Kemalpasa and Menemen. Furthermore, Kemalpasa region has been heavily affected from tannery and textile industries effl uents. Moreover, pollution parameters have not been infl uenced by changes in physical factors (discharge and temperature). This study indicated the effectiveness of water quality index approach and statistical tools in fi ngerprinting of pollution and comparative assessment of water quality. Both methods can assist decision makers to determine priorities in management practices.
Lean manufacturing has been the most deliberated concept ever since its introduction. Many organization across the world implemented lean concept and witnessed dramatic improvements in all contemporary performance parameters. Lean manufacturing has been a sort of mirage for the Indian automotive industry. The present research investigated the key lean barriers to lean implementation through literature survey, confirmatory factor analysis, multiple regression, and analytic network process. The general factors to lean implementation were inadequate lean planning, resource constraints, half-hearted commitment from management, and behavioral issues. The most important factor in the context of lean implementation in Indian automotive industry was inadequate lean planning found with the help of confirmatory factor analysis and multiple regression analysis. Further analysis of these extracted factors through analytic network process suggested the key lean barriers in Indian automotive industry, starting from the most important were absence of proper lean implementation methodology, lack of customer focus, absence of proper lean measurement system, inadequate capital, improper selection of lean tools & practices, leadership issues, resistance to change, and poorly defined roles & responsibilities. Though literature identifying various lean barriers are available. The novelty of current research emerges from the identification and subsequent prioritization of key lean barriers within Indian automotive SMEs environment. The research assists in smooth transition from traditional to lean system by identifying key barriers and developing customized framework of lean implementation for Indian automotive SMEs.
This document analyses qualities of methods used for testing dynamical parameters of Digital-to-Analog Converters (DAC) using a multi-frequency signal. As the source for these signals, Amplitude Modulated (AM) and Frequency Modulated (FM) signals are used. These signals are often used in radio engineering. Results of the tests, like Effective Number of Bits (ENOB), Signal-to-Noise and Distortion (SINAD), are evaluated in the frequency domain and they are compared with standard results of Sine Wave FFT test methods. The aim of this research is firstly to test whether it is possible to test a DAC using modulated signals, secondly to reduce testing time, while estimating band performance of DAC.