The quality of power in modern-day power system is polluted with increased penetration of converter-based distributed generations such as wind farm, solar PV system. In such scenarios detection of islanding and power quality disturbances as well as the removal of these from the system is quite crucial for equipment and maintenance personnel safety. Here, a down-sampling empirical mode decomposition (DEMD) and optimized random forest (RF) machine learning approach are hybridized to detect islanding conditions with reduced non-detection zone (NDZ) and classify non-islanding power quality events in a highly wind energy penetrated distribution generation system. DEMD has a special ability to filter out the fundamental signal from the polluted signal and random forest is quite an unbiased non-linear machine learning approach. Moreover, an improved grey wolf optimization technique is proposed to optimize the parameter of RF. The proposed technique is simulated in MATLAB/Simulink with IEEE 13-Bus test grid. The efficacy of the proposed method is evaluated through comparative analysis with existing machine learning techniques under normal and noisy environments as well as validated in narrow NDZ with lesser detection time.
A novel islanding detection technique by hybridising empirical mode decomposition (EMD) and multi-scale mathematical morphology (MMM) is proposed to detect the islanding condition in a distributed generation system to ensure personnel and equipment safety. The proposed method first uses EMD to efficiently separate the collected raw signal into the number of intrinsic mode functions (IMFs) with different frequency scales and the signal is reconstructed considering important IMFs which carry transient features for further analysis using their correlation coefficients. MMM is used for determining a ratio index named as MMMRI, the threshold value of the proposed MMMRI decides islanding and other power quality (PQ) disturbances. The proposed hybrid method name coined as EMD-MMMRI. The main motivation behind hybridising two signal processing techniques is to reduce detection time and improve accuracy. The efficacy of the method is demonstrated for different PQ disturbances and islanding events simulated on a grid-connected, heavily wind energy penetrated distributed generation system using MATLAB/Simulink environment. The test bench validation of the proposed technique is obtained through TMS 320C6713 Starter Kit (DSK) in digital signal processor platform. The efficacy of proposed work is demonstrated with large number of simulation studies.
This paper presents a modified TLBO (teaching-learning-based optimization) approach for the local linear radial basis function neural network (LLRBFNN) model to classify multiple power signal disturbances. Cumulative sum average filter has been designed for localization and feature extraction of multiple power signal disturbances. The extracted features are fed as inputs to the modified TLBO-based LLRBFNN for classification. The performance of the proposed modified TLBO-based LLRBFNN model is compared with the conventional model in terms of convergence speed and classification accuracy. Also, an extreme learning machine (ELM) approach is used to optimize the performance of the proposed LLRBFNN and is compared with the TLBO method in classifying the multiple power signal disturbances. The classification results reveal that although the TLBO approach produces slightly better accuracy in comparison with the ELM approach, the latter is much faster in implementation, thus making it suitable for processing large quantum of power signal disturbance data.
Background: Dengue has broad clinical presentation with unpredictable clinical evolution and outcome while most patients recover following a self-limiting non-severe clinical course, a small proportion progress to severe disease. As early diagnosis of dengue infection remains a challenge around the world in areas of limited resources, laboratory parameters like CRP, Neutrophil counts may serve as predictive markers to promote early diagnosis. The objectives of this study were to stratify the levels of C-reactive protein and Neutrophil counts in children with dengue fever and to determine the correlation of C-reactive protein and Neutrophil counts with the severity of dengueMethods: This was an Observational chart based descriptive study done in all pediatric dengue children (aged 1-15 years) admitted at Father Muller medical college hospital, Mangalore during the period of June 2014 to 2016. Total sample size was 100. Data collection was done by using purposive sampling based on inclusion and exclusion criteria from case records. Controls (n = 20), children with diagnosis of viral fever were considered in the study.Results: Out of the 100 children studied, 16% were <5 years ,33% between 6-10 years and 51% above 10 years of age. Mean CRP levels in NS1, IgM and both are 6.2, 6.9, 6.3. CRP values >5 were considered as positive. Mean CRP values in dengue fever with warning signs (DF1), without warning signs (DF2) and Severe Dengue (DF3) were 6.3, 6.2, 11.4 respectively. Absolute Neutropenia was observed in 52% of the study population of dengue (DF1) of which severe neutropenia was observed in 19% and 15% OF DF2 (with no warning signs) also showed neutropenia. CRP values are significant in the study when compared to controls and absolute neutropenia was observed in 52% of dengue with warning signs. Hence CRP and neutropenia may be helpful as early predictors of severe dengue.Conclusions: Our study was an attempt to correlate CRP and neutropenia for early prediction of severe dengue. Mean CRP values in the population were significant statically but not as markedly elevated in other bacterial illness as the study population have no enrolled cases of severe dengue. But neutropenia (<1,500/cmm) and positive CRP (>5) may serve as predictive markers in a resource limited setting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.