Search

Wireless multipath clustering is an important area in channel modeling, and an accurate channel model can lead to a reliable wireless environment. Finding the best technique in clustering wireless multipath is still challenging due to the radio channels’ time-variant characteristics. Several clustering techniques have been developed that offer an improved performance but only consider one or two parameters of the multipath components. This study improved the K-PowerMeans technique by incorporating weights or loads based on the principal component analysis and utilizing the Minkowski distance metric to replace the Euclidean distance. K-PowerMeans is one of the several methods in clustering wireless propagation multipaths and has been widely studied. This improved clustering technique was applied to the indoor datasets generated from the COST 2100 channel Model and considered the multipath components’ angular domains and their delay. The Jaccard index was used to determine the new method’s accuracy performance. The results showed a significant improvement in the clustering of the developed algorithm than the standard K-PowerMeans.

The electroencephalogram (EEG) signals being a recording of the electrical activity of the brain provides valuable information in the analysis of its function and disorder. Epilepsy is a brain disorder characterized by uncontrolled excessive activity. Repeated abnormal disturbance or seizure causes epilepsy. Hence, EEG signals act as a diagnostic tool for epilepsy. An approach based on tree-based pipeline optimization tool (TPOT) is presented for classification of EEG signals as either seizure or normal activity in the brain. A binarized dataset with sampled signal levels and the corresponding class is subjected to a genetic approach for acquiring an optimized predictive model. In TPOT, the tedious process involved in machine learning being repeatedly performed until arriving at the best solution is automated using genetic algorithm, i.e., evaluate-select-crossover-mutate is repeated to tune the pipeline. In the settings used in this paper, there are 90 pipeline configurations for evaluation for which around 450 models are fitted and evaluated against the training data in one grid search. The best pipeline is the one with the highest cross-validation score in the run at 95.94%. The test accuracy is at 95.27% which is just a little lower than the cross-validation score. The predictive model consists of pre-processing steps Maximum Absolute Scaler and Function Transformer which is utilized by a Gaussian Naive Bayes classifier. The system is trained and tested for epileptic seizure detection using raw EEG signals. The optimized features and predictor obtained via TPOT resulted to a high-performance accuracy for epileptic seizure detection.

Pulsars enabled astronomers to study neutron stars and verify general relativity under intense gravitational field conditions. However, finding pulsars is not as easy as it seems because most of them have weak pulses that get drowned in the background noise and hence do not get detected. This paper presents a novel way of classifying radio emission patterns collected from a radio telescope whether it is from a pulsar or not through machine learning and genetic algorithm. The dataset was acquired from the High Time Resolution Universe (HTRU) survey two which contains eight numerical features and one target variable describing the pulse profile. Synthetic Minority Oversampling Technique (SMOTE) was applied to the dataset to fix the imbalance between classes. A genetic algorithm library was used to automatically select the best feature preprocessing method, feature selection/reduction technique, machine learning model inside the scikit-learn library, and hyperparameter settings. The genetic algorithm suggested using a single stack and multiple stack classifiers for different sets of features. The optimum level of hyperparameters was also given with the help of the same algorithm. The selected pipelines consistently reported a score of more than 99% in all the evaluation metrics used.

Proposed datasets for the interim goal of validating and comparing multipath clustering approaches are put forward based on the COST 2100 channel model (C2CM), which is a geometry-based stochastic channel model (GSCM) that can replicate multiple-input multiple-output (MIMO) channels. This paper provides descriptions and characteristics of the multipaths drawn from the Matlab implementation of the C2CM in eight indoor and semi-urban channel scenarios at 5.3 GHz and 285 MHz, respectively. In addition to the multipaths generated, the meaning and extraction method of the multipath components (MPCs) and the multipath clusters are elucidated. The suggested datasets are at the IEEE DataPort repository for use widely for the propagation engineering community.

This paper presents a classification algorithm for air quality index (AQI) using fuzzy logic (FL) system. AQI tells the level of cleanliness of the air and provides a corresponding health warning. In this study, two types of input pollutants are only considered which are the carbon monoxide (CO) and nitrogen dioxide (NO 2 ). Each input is classified into six categories that include very low, low, moderate, high, very high and extremely high. Mamdani fuzzy inference system (FIS) is used to process the FL system giving an output of AQI values expressed in six categories: good, moderate, unhealthy for sensitive groups, unhealthy, very unhealthy and hazardous. Simulation is performed using MATLAB fuzzy logic toolbox, which provides effective and reliable results.