The combined system of micro-CT and fluorescence molecular tomography (FMT) offers a new tool to provide anatomical and functional information of small animals in a single study. To take advantages of the combined sys...
详细信息
The combined system of micro-CT and fluorescence molecular tomography (FMT) offers a new tool to provide anatomical and functional information of small animals in a single study. To take advantages of the combined system, a data preprocessing method is proposed to extract the valid data for FMT reconstruction algorithms using a priori information provided by CT. The boundary information of the animal and animal holder is extracted from reconstructed CT volume data. A ray tracing method is used to trace the path of the excitation beam, calculate the locations and directions of the optional sources and determine whether the optional sources are valid. To accurately calculate the projections of the detectors on optical images and judge their validity, a combination of perspective projection and inverse ray tracing method are adopted to offer optimal performance. The imaging performance of the combined system with the presented method is validated through experimental rat imaging.
For construction to progress smoothly, effective cost estimation is vital, particularly in the conceptual and schematic design stages. In these early phases, despite the fact that initial estimates are highly sensitiv...
详细信息
For construction to progress smoothly, effective cost estimation is vital, particularly in the conceptual and schematic design stages. In these early phases, despite the fact that initial estimates are highly sensitive to changes in project scope, owners require accurate forecasts which reflect their supplying information. Thus, cost estimators need reliable estimation strategies. In practice, parametric cost estimation, which utilizes historical cost data, is the most commonly used method in these initial phases. Therefore, compilation of historical data pertaining to appropriate cost variance governing parameters is a prime requirement. However, data mining (data preprocessing) for denoising internal errors or abnormal values must be performed before this compilation. To address this issue, this research proposes a statistical methodology for data preprocessing. Moreover, a statistically preprocessed data-based parametric (SPBP) cost model is developed based on multiple regression equations. Case studies of Korean construction projects verify that the model enhances cost estimate accuracy and reliability than conventional cost models.
Objective: Electrical impedance tomography (EIT) is a promising measurement technique in applications, especially in industrial monitoring and clinical diagnosis. However, two major drawbacks exist that limit the spat...
详细信息
Objective: Electrical impedance tomography (EIT) is a promising measurement technique in applications, especially in industrial monitoring and clinical diagnosis. However, two major drawbacks exist that limit the spatial resolution of reconstructed EIT images, i.e. the 'soft field' effect and the ill-posed problem. In recent years, apart from the development of reconstruction algorithms, some preprocessing methods for measured data or sensitivity maps have also been proposed to reduce these negative effects. It is necessary to find the optimal preprocessing method for various EIT reconstruction ***: In this paper, seven typical data preprocessing methods for EIT are reviewed. The image qualities obtained using these methods are evaluated and compared in simulations, and their applicable ranges and combination effects are *** results: The results show that all the reviewed methods can enhance the quality of EIT reconstructed images to different extents, and there is an optimal one under any given reconstruction algorithm. In addition, most of the reviewed methods do not work well when using the Tikhonov regularization ***: This paper introduces the preprocessing method to EIT, and the quality of reconstructed images obtained using these methods is evaluated through simulations. The results can provide a reference for practical applications.
Visible-near infrared spectroscopy was successfully used for the determination of total hemoglobin concentration in whole blood. Absorption spectra of whole blood samples, whose hemoglobin concentrations ranged betwee...
详细信息
Visible-near infrared spectroscopy was successfully used for the determination of total hemoglobin concentration in whole blood. Absorption spectra of whole blood samples, whose hemoglobin concentrations ranged between 6.6 and 17.2 g/dL, were measured from 500 to 800 nm. Two different types of transmission were measured: conventional transmission spectroscopy which collected primarily collimated radiation transmitted through the sample, and total transmission spectroscopy which used an integrating sphere to collect all scattered light as well, Different preprocessing techniques in conjunction with a partial least squares regression calibration model to predict hemoglobin concentrations were applied to the above two types of transmission, Depending on different preprocessing methods, the standard error of predictions ranged from 0.37 to 2.67 g/dL, Mean centering gave the most accurate prediction in our particular data set. preprocessing methods designed for compensation of the scattering effect produced the worst results contrary to expectations. For univariate analysis, better prediction was achieved by total transmission measurement than by conventional transmission measurement, No significant difference was observed for multivariate analysis on the other hand, Careful selection of the data preprocessing methods and of the multivariate statistical model is required for reagentless determination of hemoglobin concentration in whole blood. (C) 2001 Society of Photo-Optical Instrumentation Engineers.
In this study, an artificial autoassociative neural network (AANN) was used online to detect deviations from normal antibiotic production fermentation using conventional process variables. To improve the efficiency of...
详细信息
In this study, an artificial autoassociative neural network (AANN) was used online to detect deviations from normal antibiotic production fermentation using conventional process variables. To improve the efficiency of extracting hidden information contained in multidimensional process variables, and to finally render the AANN adequate for fault detection, we explored the following methods: selection of process variables;preprocessing of data that involved normalizing the training data of the AANN;and evaluation of data that involved assessing the output of the AANN. A method for fault detection in virginiamycin M and S production by Streptomyces virginiae was successfully developed based on these techniques.
This paper describes a data preprocessing algorithm that can be used to mitigate the effects of interfering spectral components when the goal is to detect the spectrum of unknown components in a mixture of known compo...
详细信息
This paper describes a data preprocessing algorithm that can be used to mitigate the effects of interfering spectral components when the goal is to detect the spectrum of unknown components in a mixture of known components or to verify the presence of suspected components in the spectrum of a mixture of known components. The algorithm is both relatively simple and applicable to a wide range of problems in spectroscopy. The range of applicability can be increased by combining the method with other data preprocessing methods, for example derivative spectra, and can also accommodate variability in the spectra of one or more of the known components. Examples of the application of the algorithm to real problems are given for near-infrared analysis of antibiotic drug formulations inside gelatin capsules and mid-infrared analysis of atmospheric pollutants.
The evaluation of surface water resources is a necessary input to solving water management problems. Neural network models have been trained to predict monthly runoff for the Tirso basin, located in Sardinia (Italy) a...
详细信息
The evaluation of surface water resources is a necessary input to solving water management problems. Neural network models have been trained to predict monthly runoff for the Tirso basin, located in Sardinia (Italy) at the S. Chiara section. Monthly time series data were available for 69 years and are characterized by non-stationarity and seasonal irregularity, which is typical of a Mediterranean weather regime. This paper investigates the effects of data preprocessing on model performance using continuous and discrete wavelet transforms and data partitioning. The results showed that networks trained with pre-processed data performed better than networks trained on undecomposed, noisy raw signals. In particular, the best results were obtained using the data partitioning technique. (c) 2006 Elsevier Ltd. All rights reserved.
In situ measurement techniques are promising tools to aid process development. However, they also pose new challenges in evaluating large amounts of recorded data. A new procedure for in situ laser-backscattering devi...
详细信息
In situ measurement techniques are promising tools to aid process development. However, they also pose new challenges in evaluating large amounts of recorded data. A new procedure for in situ laser-backscattering devices has been developed that allows transformation of the raw recorded data, a chord length distribution, into a format suitable for population balance modeling. Emphasis is thereby laid on the influence of the suspension density on the measured data. Experimental data are recorded using a batch laboratory crystallizer equipped with an in situ 3D-ORM laser backscattering device and an ultrasound probe. The new proposed five-step procedure for data preprocessing is based on several independently developed tools from literature and is exemplarily illustrated with results on the crystallization of ascorbic acid. The proposed method is a step forward to use in situ laser-backscattering devices also for quantitative purposes.
Although data preprocessing is a universal technique that can be widely used in neural networks (NNs), most research in this area is focused on designing new NN architectures. This paper, we propose a preprocessing te...
详细信息
Although data preprocessing is a universal technique that can be widely used in neural networks (NNs), most research in this area is focused on designing new NN architectures. This paper, we propose a preprocessing technique that enriches the original image data using local intensity information;this technique is motivated by human perception. To encode this information into an image, we introduce a new image structure named image represented by a fuzzy function. When using this structure, a crisp intensity value of each pixel is replaced by a fuzzy set given by a membership function constructed with the usage of extremal values from the particular neighborhood of that pixel. We describe this structure and its properties and propose a way in which it can he used as an input into existing NNs without any modifications. Based on our benchmark consisting of three well-known datasets and five NN architectures, we show that the proposed preprocessing can, in mast cases, decrease classification error compared with a baseline and two other preprocessing methods. To support our claim, we have also selected several publicly available projects and tested the impact of the preprocessing with a positive result.
暂无评论