Spectral Extraction Algorithm Research Articles

Location and spectral extraction algorithm for a static broadband snapshot imaging spectrometer

Location and spectral extraction algorithm for a static broadband snapshot imaging spectrometer

LBP–Bilateral Based Feature Fusion for Breast Cancer Diagnosis

Since reporting cases of breast cancer are on the rise all over the world. Especially in regions such as Pakistan, Saudi Arabia, and the United States. Efficient methods for the early detection and diagnosis of breast cancer are needed. The usual diagnosis procedures followed by physicians has been updated with modern diagnostic approaches that include computer-aided support for better accuracy. Machine learning based practices has increased the accuracy and efficiency of medical diagnosis, which has helped save lives of many patients. There is much research in the field of medical imaging diagnostics that can be applied to the variety of data such as magnetic resonance images (MRIs), mammograms, X-rays, ultrasounds, and histopathological images, but magnetic resonance (MR) and mammogram imaging have proved to present the promising results. The proposed paper has presented the results of classification algorithms over Breast Cancer (BC) mammograms from a novel dataset taken from hospitals in the Qassim health cluster of Saudi Arabia. This paper has developed a novel approach called the novel spectral extraction algorithm (NSEA) that uses feature extraction and fusion by using local binary pattern (LBP) and bilateral algorithms, as well as a support vector machine (SVM) as a classifier. The NSEA with the SVM classifier demonstrated a promising accuracy of 94% and an elapsed time of 0.68 milliseconds, which were significantly better results than those of comparative experiments from classifiers named Naïve Bayes, logistic regression, K-Nearest Neighbor (KNN), Gaussian Discriminant Analysis (GDA), AdaBoost and Extreme Learning Machine (ELM). ELM produced the comparative accuracy of 94% however has a lower elapsed time of 1.35 as compared to SVM. Adaboost has produced a fairly well accuracy of 82%, KNN has a low accuracy of 66%. However Logistic Regression, GDA and Naïve Bayes have produced the lowest accuracies of 47%, 43% and 42%.

A Light-Sheet-Based Imaaging Spectrometer to Characterize Acridine Orange Fluorescence within Leukocytes.

Low-cost imaging systems that utilize exogenous fluorescent dyes, such as acridine orange (AO), have recently been developed for use as point-of-care (POC) blood analyzers. AO-based fluorescence imaging exploits variations in emission wavelength within different cell types to enumerate and classify leukocyte subpopulations from whole blood specimens. This approach to leukocyte classification relies on accurate and reproducible colorimetric features, which have previously been demonstrated to be highly dependent on the cell staining protocols (such as specific AO concentration, timing, and pH). We have developed a light-sheet-based fluorescence imaging spectrometer, featuring a spectral resolution of 9 nm, with an automated spectral extraction algorithm as an investigative tool to study the spectral features from AO-stained leukocytes. Whole blood specimens were collected from human subjects, stained with AO using POC methods, and leukocyte spectra were acquired on a cell-by-cell basis. The post-processing method involves three steps: image segmentation to isolate individual cells in each spectral image; image quality control to exclude cells with low emission intensity, out-of-focus cells, and cellular debris; and the extraction of spectra for each cell. An increase in AO concentration was determined to contribute to the red-shift in AO-fluorescence, while varied pH values did not cause a change in fluorescence. In relation to the spectra of AO-stained leukocytes, there were corresponding red-shift trends associated with dye accumulation within acidic vesicles and at increasing incubation periods. The system presented here could guide future development of POC systems reliant on AO fluorescence and colorimetric features to identify leukocyte subpopulations in whole blood specimens.

An Automated Feature Extraction Algorithm for Diagnosis of Gear Faults

Gears are used for the transfer of mechanical power and are an important part of the electromechanical transmission system. Unexpected failure of gear could cause shutdown of the machines and proves to be expensive in terms of production loss and maintenance. Therefore, reliable condition monitoring is required to protect unexpected gear failures. It has been highlighted in the recently published literature that the gear faults appear at the specific gear frequencies in the instantaneous power spectrum of the motor. However, the amplitudes of these gear frequencies are very small and are shadowed by the environment noise. Thus, reliable diagnosis of gear faults is a challenge in real-time fault diagnosis systems. This issue has been addressed in this paper through the development of the automated spectral extraction algorithm. The theoretical investigation has been verified through the custom-designed experimental test rig.

Periodicity-based swimming performance feature extraction and parameter estimation

This paper presents a novel approach for extracting swimming performance parameters from accelerometer data using techniques traditionally applied to audio analysis. The recorded acceleration data is treated as sampled audio data, with the stroke rate (one of the main parameters to extract) treated as the fundamental frequency. A pitch detection algorithm is then adapted to this domain and applied to the data. Lap counts are derived from an analysis of the output frequency series as percussive events, and stroke counts are obtained from a pitch-aligned adaptive spectral extraction algorithm. This approach was compared to conventional accelerometer data analysis techniques (peak detection and zero crossing) and demonstrated superior accuracy compared to a visual observation criterion. For stroke count determination, the new approach had zero error rates of 86.1 % (versus 58.3 % for the zero-crossing method) and 75 % (versus 60 % for peak detection) for lower-back and wrist placement locations, respectively. Additionally, this new approach is not dependent on filtering, and is robust to sensor displacement and axial alignment.

Spectral Extraction Algorithm for LAMOST Two-dimensional Fiber-spectroscopic Images

This paper describes the method of spectral extraction to be used for the data processing of LAMOST's two-dimensional fiber-spectroscopic images. The effect of the selection of sampling points on the result of spectral extraction is analyzed. Based on the characteristics of Gaussian distribution functions and some experiments, the selection range of sampling points is defined, and the problem that some negative flux values appear in the result of spectral extraction is resolved. In addition, aiming at the problem that rather large errors exist in the result of spectral extraction under strong noise background, an improved extraction method based on the frequency-domain filtering is proposed. By using the FFT and low-pass filter, the sharp noises affecting the real fiber profiles are removed at first, before the normal spectral extraction is performed. Experiments and tests are made by using the simulative data provided by the data processing system of the LAMOST telescope, and the results indicate that the improved extraction method is feasible and effective.