Psoriasis Lesion Detection Using Hybrid Seeker Optimization Based Image Clustering

Background: In recent years, there has been a massive increase in the number of people suffering from psoriasis. For proper psoriasis diagnosis, psoriasis lesion segmentation is a pre-requisite for quantifying the severity of this disease. However, segmentation of psoriatic lesion cannot be evaluated just by visual inspection as they exhibit inter and intra variability among the severity classes. Most of the approaches currently pursued by dermatologists are subjective in nature. The existing conventional clustering algorithm for objective segmentation of psoriasis lesion suffers from limitations of premature local convergence. Objective: An alternative method for psoriatic lesion segmentation with the objective analysis is sought in the present work. The present work aims at obtaining optimal lesion segmentation by adopting an evolutionary optimization technique which possesses a higher probability of global convergence for psoriasis lesion segmentation. Method: A hybrid evolutionary optimization technique based on the combination of two swarm intelligence algorithms; namely Artificial Bee Colony and Seeker Optimization algorithm has been proposed. The initial population for the hybrid technique is obtained from the two conventional local-based approaches i.e. Fuzzy C-means and K-means clustering algorithms. Results: The initial population selection from the convergence of classical techniques reduces the effect of population dynamics on the final solution and hence yields precise lesion segmentation with Jaccard Index of 0.91 from 720 psoriasis images. Conclusion: The performance comparison reflects the superior performance of the proposed algorithm over other swarm intelligence and conventional clustering algorithms.

Genetic Algorithm with Elitist-Tournament for Clashes-Free Slots of Lecturer Timetabling Problem

<span>Genetic algorithm (GA) approach is one of an evolutionary optimization technique relies on natural selection. The employment of GA still popular and it was applied to many real-world problems, especially in many combinatorial optimization solutions. Lecturer Timetabling Problem (LTP) has been researched for a few decades and produced good solutions. Although, some of LTP offers good results, the criteria and constraints of each LTP however are different from other universities. The LTP appears to be a tiresome job to the scheduler that involves scheduling of students, classes, lecturers and rooms at specific time-slots while satisfying all the necessary requirements to build a feasible timetable. This paper addresses the employment and evaluation of GA to overcome the biggest challenge in LTP to find clashes-free slots for lecturer based on a case study in the Faculty of Computer and Mathematical Sciences, University Technologi MARA, Malaysia. Hence, the performance of the GA is evaluated based on selection, mutation and crossover using different number of population size. A comparison of performance between simple GA with Tournament Selection scheme combined with Elitism (TE) and a GA with Tournament (T) selection scheme. The findings demonstrate that the embedded penalty measures and elitism composition provide good performance that satisfies all the constraints in producing timetables to lecturers. </span>

Comparison Of Cascaded H-bridge Inverters for Harmonic Mitigation Considering Various Loads

This paper compares the reduction of harmonics in various level cascaded H-bridge inverters. The switching angles for the cascaded H-bridge inverter were calculated by evolutionary optimization technique. Fourier analysis is used to determine the switching angles for the desired electrical parameters. Lower order harmonics such as third, fifth, seventh, ninth and eleventh order harmonics were taken into consideration to reduce the total harmonic distortion. Simulation was done for thirteen, fifteen and seventeen level cascaded H-bridge inverters using Matlab. Total harmonic distortion of voltage and current for R, RL and Motor load were analyzed.