Over the past decade, several studies have been conducted to discover a better-performing multipath clustering technique. Developing a multipath clustering technique with better accuracy performance is a big challenge considering the varying properties of the multipath propagations that change over time. In this study, several clustering techniques have been investigated and compared to the newly-developed technique for performance analysis. Using the Jaccard score as a metric for the accuracy of grouping correctly the wireless multipaths, the performance of the different clustering techniques has been determined and compared to the newly-developed technique. The proposed clustering algorithm shows improved performance in the indoor channel scenarios but needs further investigation in the semi-urban environment.

Diabetes mellitus is a disease incorporated with carbohydrate metabolism whereas the body becomes unable to generate or react with insulin which leads to abnormal levels of blood sugar (glucose). In a worldwide perspective, Diabetes mellitus is ranked as the 9th leading cause of death based on the records of the World Health Organization and according to the International Diabetes Federation, there are about 463 million diabetic people worldwide in 2019 which is projected to increase to 700 million diabetic people by year 2045. In a regional perspective, about 251 million (45%) diabetic people resides on the Western Pacific and Southeast Asian region, whereas about 140 million people are undiagnosed of the disease. In this study, a genetic algorithm-optimized neural network using MATLAB was developed based on the risk factors. The experimental results show that the best validation performance has a value of 0.014129 and with a regression model coefficient R2 value of 0.95864.

The liver is the human body's largest internal organ. Globally, liver disease is considered the cause of approximately 2 million yearly death - whereas the 11th and 16th worldwide leading causes of death are cirrhosis and liver cancer. In the Philippines, according to the Department of Health (DOH), liver cancer is ranked as the 3rd leading cause of death. In most cases, surgery may be considered a possible cure if detected at an early stage. However, there is no efficient early detection method for liver cancer. In this paper, multiple machine learning methodologies are modeled to provide diagnosis classification of liver disease based on the laboratory parameter readings. Based on the results for all models, the most accurate prediction is made by ANN at 89%, followed by SVM at 79.5%. The results establish that AI-based machine learning approaches may be utilized for assisting medical-related diagnosis.

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.

Data analysis is an integral part of research. Most researchers examine their results by using graphs, tables, charts, and figures. These methods are effective, but knowledge transfer is limited because it only depends on what the authors or researchers have presented. The need to scrutinise further the given data is essential. One way of addressing this problem is to utilise a graphical user interface (GUI), wherein a user can manually choose some parameters of an extensive dataset to display and analyse. In this paper, the results of the four variants of clustering techniques, namely the Ant Colony Optimization (ACO), Gaussian Mixture Model (GMM), K-Power Means (KPM), and Kernel-Power Density-Based Estimation (KPD), in grouping the wireless multipath propagations, are evaluated through the use of a GUI. The accuracy performance of each clustering algorithm can be obtained by choosing in the GUI the corresponding channel scenario that the user would like to investigate. A deeper analysis of the clustering characteristics can also be done by selecting other parameters in the GUI. This selection gives a better understanding of the behaviour of each clustering technique and provides an effective way of presenting and analysing the different sets of data.