Design of Water Wave Optimization with Extreme Learning Machine for Mental Health Assessment with Chronic Diseases

Abstract

Given the importance of dental health to physical health, there has been a lack of attention paid to this issue among those with mental health issues. Start-ups have originated as primary drivers of job creation and economic development and frequently act as an accelerator for radical innovation. New firms account for nearly 20% of employment but create nearly half of new jobs, and innovation by early companies substantially adds to collective productivity growth, responsible for half of it in the United States. At the time of the corona virus (COVID-19) crisis, start-ups remained to act crucial roles in economy. Few creative young companies have responded rapidly and adaptable to the pandemic, and were critical in aiding most of the country's shift towards fully-digital, health services education, and work and have granted innovations in medical services and goods. Therefore, it is needed to design effectual financial crisis prediction models for start-ups during COVID-19 pandemic. This study aims to develop a water wave optimization with extreme learning machine (WWO-ELM) for predicting financial status of the startups. The presented WWO-ELM model primarily normalizes the financial data to transform them into a compatible format. Then, Consistency‐based feature selection (CBFS) model is utilized to elect a set of effectual features. Next, the ELM model receives the features as input to carry out the classification process. At last, the WWO algorithm is applied to tune the parameters related to the ELM model and thereby results in improved outcomes. The experimental assessment of the WWO-ELM model highlighted the better performance of the WWO-ELM model over other models.