The electronic nose (e-nose) is a compact, intelligent sensing system that mimics the human sense of smell. It consists of an array of gas sensors that imitate the olfactory receptors of the nose, combined with intelligent pattern recognition capabilities similar to those of humans. It is capable of distinguishing between different odors. To date, e-noses have been applied in various fields, ranging from health and environmental monitoring to robotic systems. The next generation involves the integration of artificial olfaction-based e-noses within more complex systems. This paper addresses a critical challenge for e-noses, which is indoor location recognition based on the odors detected. Our designed e-nose uses six metal oxide sensors to capture an array of six values that represent the odor profile of a specific location. Using these odor profiles, a dataset was collected that included six different places within an indoor environment. To distinguish between the odors associated with these locations, a deep learning approach was applied, proposing two neural network models for odor classification. The identified classes are then associated with their corresponding locations. Despite the inherent limitations of e-noses, the results of our work are promising. Our system can be integrated into a robotic application to close the loop during navigation.