NASA has designed and publicized a standard benchmark problem for propulsion engine gas path diagnostic that enables comparisons among different engine diagnostic approaches. Some traditional model-based approaches and novel purely data-driven approaches such as machine learning, have been applied to this problem.
This study focuses on a different machine learning approach to the diagnostic problem. Some most common machine learning techniques, such as support vector machine, multi-layer perceptron, and self-organizing map are used to help gain insight into the different engine failure modes from the perspective of big data. They are organically integrated to achieve good performance based on a good understanding of the complex dataset.
The study presents a new hierarchical machine learning structure to enhance classification accuracy in NASA's engine diagnostic benchmark problem. The designed hierarchical structure produces an average diagnostic accuracy of 73.6%, which outperforms comparable studies that were most recently published.
The primary purpose of this paper is to evaluate the energy impacts of faults in building heating, ventilation, and air conditioning systems and determine which systems’ faults have the highest effect on the energy consumption. With the knowledge obtained through the results described in this paper, building engineers and technicians will be more able to implement a data-driven solution to building fault detection and diagnostics
In the United States alone, commercial buildings consume 18% of the country’s energy. Due to this high percentage of energy consumption, many efforts are being made to make buildings more energy efficient. Heating, ventilation, and air conditioning (HVAC) systems are made to provide acceptable air quality and thermal comfort to building occupants. In large buildings, a demand-controlled HVAC system is used to save energy by dynamically adjusting the ventilation of the building. These systems rely on a multitude of sensors, actuators, dampers, and valves in order to keep the building ventilation efficient. Using a fault analysis framework developed by the University of Alabama and the National Renewable Energy Laboratory, building fault modes were simulated in the EnergyPlus whole building energy simulation program. The model and framework are based on the Department of Energy’s Commercial Prototype Building – Medium Office variant. A total of 3,002 simulations were performed in the Atlanta climate zone, with 129 fault cases and 41 fault types. These simulations serve two purposes: to validate the previously developed fault simulation framework, and to analyze how each fault mode affects the building over the simulation period.
The results demonstrate the effects of faults on HVAC systems, and validate the scalability of the framework. The most critical fault cases for the Medium Office building are those that affect the water systems of the building, as they cause the most harm to overall energy costs and occupant comfort.
Background: Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ~60% of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM.
Methods: We recruited primary GBM patients undergoing image-guided biopsies and acquired pre-operative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs <80% tumor nuclei) for corresponding samples. In a training set, we used three texture analysis algorithms and three ML methods to identify MRI-texture features that optimized model accuracy to distinguish tumor content. We confirmed model accuracy in a separate validation set.
Results: We collected 82 biopsies from 18 GBMs throughout ENH and BAT. The MRI-based model achieved 85% cross-validated accuracy to diagnose high- vs low-tumor in the training set (60 biopsies, 11 patients). The model achieved 81.8% accuracy in the validation set (22 biopsies, 7 patients).
Conclusion: Multi-parametric MRI and texture analysis can help characterize and visualize GBM’s spatial histologic heterogeneity to identify regional tumor-rich biopsy targets.
Asymmetry of bilateral mammographic tissue density and patterns is a potentially strong indicator of having or developing breast abnormalities or early cancers. The purpose of this study is to design and test the global asymmetry features from bilateral mammograms to predict the near-term risk of women developing detectable high risk breast lesions or cancer in the next sequential screening mammography examination. The image dataset includes mammograms acquired from 90 women who underwent routine screening examinations, all interpreted as negative and not recalled by the radiologists during the original screening procedures. A computerized breast cancer risk analysis scheme using four image processing modules, including image preprocessing, suspicious region segmentation, image feature extraction, and classification was designed to detect and compute image feature asymmetry between the left and right breasts imaged on the mammograms. The highest computed area under curve (AUC) is 0.754 ± 0.024 when applying the new computerized aided diagnosis (CAD) scheme to our testing dataset. The positive predictive value and the negative predictive value were 0.58 and 0.80, respectively.