An intelligent framework for productivity assessment and analysis of human resource from resilience engineering, motivational factors, HSE and ergonomics perspectives

Human resource management (HRM) is the description of formal systems planned for the manpower management in a company. HRM aims to maximize organizational productivity by optimizing efficiency and effectiveness of its personnel. This paper presents an intelligent framework for productivity assessment and analysis of human resource in a large petrochemical plant. The efficiency and effectiveness of this company's staff are evaluated by considering three concepts including resilience engineering (RE), motivational factors in the work environment and health, safety, environment and ergonomics (HSEE). The framework is based on using Data Envelopment Analysis (DEA) for calculating efficiency and one of the well-known Artificial Neural Networks (ANNs), namely Multi-Layer Perceptron (MLP) besides an Adaptive Neuro Fuzzy Inference System (ANFIS) trained by two evolutionary methods; particle swarm optimization (PSO) and genetic algorithm (GA) for evaluating effectiveness of the company's workforce. Then, the productivity of staff (which is the sum of efficiency and effectiveness) is analyzed to determine the unproductive staff as well as the impact degree of each concept on efficiency and effectiveness. The proposed framework can provide considerable benefits to safety-critical systems, managers and staff e.g., identifying key factors significantly affecting the productivity of HRM.