Diabetes Detection System by Mixing Supervised and Unsupervised Algorithms

Signal Modulation Recognition System Based on Different Signal Noise Rate Using Artificial Intelligent Approach

Everyone has paid much attention to modulation-type recognition in the past few years. There are many ways to find the modulation type, but only a few good ways to deal with signals with a lot of noise. This study comes up with a way to test how well different machine learning algorithms can handle noise when detecting digital and analogue modulations. This study looks at the four most common digital and analogue modulations: Phase Shift Keying, Quadrature Phase Shift Keying, Amplitude Modulation, and Morse Code. A signal noise rate from -10dB to +25dB is used to find these modulations. We used machine learning algorithms to determine the modulation type like Decision Tree, Random Forest, Support Vectors Machine, and k-nearest neighbours. After the IQ samples had been converted to the amplitude of samples and radio frequency format, the accuracy of each method looked good. Still, in the format of the sample phase, each algorithm's accuracy was less. The results show that the proposed method works to find the signals that have noises. When there is less noise, the random forest algorithm gives better results than SVM, but SVM gives better results when there is more noise.

Predictive Model for Diagnosis of Gestational Diabetes in the Kurdistan Region by a Combination of Clustering and Classification Algorithms: An Ensemble Approach

Gestational diabetes is a type of high blood sugar that develops during pregnancy. It can occur at any stage of pregnancy and cause problems for both the mother and the baby, during and after birth. The risks can be reduced if they are early detected and managed, especially in areas where only periodic tests of pregnant women are available. Intelligent systems designed by machine learning algorithms are remodelling all fields of our lives, including the healthcare system. This study proposes a combined prediction model to diagnose gestational diabetes. The dataset was obtained from the Kurdistan region laboratories, which collected information from pregnant women with and without diabetes. The suggested model uses the clustering KMeans technique for data reduction and the elbow method to find the optimal k value and the Mahalanobis distance method to find more related cluster to new samples, and the classification methods such as decision tree, random forest, SVM, KNN, logistic regression, and Naïve Bayes are used for prediction. The results showed that using a mix of KMeans clustering, elbow method, Mahalanobis distance, and ensemble technique significantly improves prediction accuracy.