Detection of Angioectasias and Haemorrhages Incorporated into a Multi-Class Classification Tool for the GI Tract Anomalies by Using Binary CNNs

The proposed deep learning algorithm will be integrated as a binary classifier under the umbrella of a multi-class classification tool to facilitate the automated detection of non-healthy deformities, anatomical landmarks, pathological findings, other anomalies and normal cases, by examining medical endoscopic images of GI tract. Each binary classifier is trained to detect one specific non-healthy condition. The algorithm analyzed in the present work expands the ability of detection of this tool by classifying GI tract image snapshots into two classes, depicting haemorrhage and non-haemorrhage state. The proposed algorithm is the result of the collaboration between interdisciplinary specialists on AI and Data Analysis, Computer Vision, Gastroenterologists of four University Gastroenterology Departments of Greek Medical Schools. The data used are 195 videos (177 from non-healthy cases and 18 from healthy cases) videos captured from the PillCam(R) Medronics device, originated from 195 patients, all diagnosed with different forms of angioectasia, haemorrhages and other diseases from different sites of the gastrointestinal (GI), mainly including difficult cases of diagnosis. Our AI algorithm is based on convolutional neural network (CNN) trained on annotated images at image level, using a semantic tag indicating whether the image contains angioectasia and haemorrhage traces or not. At least 22 CNN architectures were created and evaluated some of which pre-trained applying transfer learning on ImageNet data. All the CNN variations were introduced, trained to a prevalence dataset of 50%, and evaluated of unseen data. On test data, the best results were obtained from our CNN architectures which do not utilize backbone of transfer learning. Across a balanced dataset from no-healthy images and healthy images from 39 videos from different patients, identified correct diagnosis with sensitivity 90%, specificity 92%, precision 91.8%, FPR 8%, FNR 10%. Besides, we compared the performance of our best CNN algorithm versus our same goal algorithm based on HSV colorimetric lesions features extracted of pixel-level annotations, both algorithms trained and tested on the same data. It is evaluated that the CNN trained on image level annotated images, is 9% less sensitive, achieves 2.6% less precision, 1.2% less FPR, and 7% less FNR, than that based on HSV filters, extracted from on pixel-level annotated training data.

A multi-channel approach for automatic microseismic event association using RANSAC-based Arrival Time Event Clustering(RATEC)

In the presence of background noise,arrival times picked from a surface microseismic data set usually include a number of false picks that can lead to uncertainty in location estimation.To eliminate false picks and improve the accuracy of location estimates,we develop an association algorithm termed RANSAC-based Arrival Time Event Clustering(RATEC)that clusters picked arrival times into event groups based on random sampling and fitting moveout curves that approximate hyperbolas.Arrival times far from the fitted hyperbolas are classified as false picks and removed from the data set prior to location estimation.Simulations of synthetic data for a 1-D linear array show that RATEC is robust under different noise conditions and generally applicable to various types of subsurface structures.By generalizing the underlying moveout model,RATEC is extended to the case of a 2-D surface monitoring array.The effectiveness of event location for the 2-D case is demonstrated using a data set collected by the 5200-element dense Long Beach array.The obtained results suggest that RATEC is effective in removing false picks and hence can be used for phase association before location estimates.

Protection and control of microgrids using dynamic state estimation

High penetration of Converter Interfaced Generations(CIGs)presents challenges in both microgrid(μGrid)circuit and other system with CIG resources,such as wind farms and PV plants.Specifically,protection challenges are mainly brought by the insufficient separation between fault and load currents,especially forμGrids in islanded operation,and the short connection length inμGrids.In addition,CIG resources exhibit limited inertia and weak coupling to any rotating machinery,which can result in large transients during disturbances.To address the above challenges,this paper proposes a Dynamic State Estimation(DSE)based algorithm for protection and control of systems with substantial CIG resources such as aμGrid.It requires a high-fidelity dynamic model and time domain(sampled value)measurements.ForμGrid circuit protection,the algorithm dependably and securely detects internal faults by checking the consistency between the circuit model and available measurements.For CIG control,the algorithm estimates the frequency at other parts of aμGrid using CIG local information only and then utilizes it to provide supplementary feedback control.Simulation results prove that DSE based protection algorithm detects internal faults faster,ignores external faults and has improved sensitivity towards high impedance faults when compared to conventional protection methods.DSE based CIG control scheme also minimizes output oscillation and transient during system disturbances.