Weighted Multi-Objective Enriched Navigation using Slender Loris Optimization Algorithm

Abstract

Urban mobility remains a major concern in smart city environments, as most navigation systems optimize routes primarily based on distance or travel time while overlooking safety factors such as crime patterns, environmental conditions, and population presence. This limitation exposes travellers particularly women, tourists, and other vulnerable groups to increased risk in unfamiliar or isolated areas. To address this issue, this paper proposes Weighted Multi-Objective Enriched Navigation using Slender Loris Optimization Algorithm (WOMEN_SLOA), a multi-objective routing framework that integrates safety indicators with conventional routing metrics for secure urban travel. Inspired by the cautious behaviour of the slender loris, the SLOA based model balances travel distance, travel time, and risk exposure during route selection. Historical crime and accident records, spatial points of interest, and mobility patterns are fused through a weighted safety-scoring scheme to estimate segment-level safety and guide path optimization. A perception-oriented component is further examined to analyse how subjective safety awareness may influence routing behaviour. Experimental results show that the proposed system reduces exposure to high-risk areas while maintaining competitive routing efficiency compared with traditional shortest-path approaches. These findings demonstrate the potential of WOMEN_SLOA for safety-aware navigation in smart city transportation systems.