Portuguese 
English 
Spanish 
3 min of reading 
0 comments 
Technology Uses Real Data to Predict Likely Actions of Missing Individuals, Guiding More Effective Strategies in Rescue Operations
Researchers from the University of Glasgow in Scotland have created an innovative computational system that can help locate missing people in nature more efficiently. The technology uses real human behavior data to predict where a lost person is most likely to be found.
AI System Simulates Human Behavior
The system was developed based on information about how lost people typically act when they are outdoors. From this data, scientists created simulated agents, controlled by algorithms, that behave similarly to real people in emergency situations.
These agents act motivated by specific goals, such as finding water, trees, roads, or shelters. They decide their movements based on factors such as their current position and what is visible around them. The idea is to simulate different psychological states that influence decisions in disorientation situations.
-
Spain pumps 3.3 million m³ of sand through floating and submerged pipelines to reconstruct 7 km of beaches in Valencia and create a coastal strip up to 150 meters wider against erosion
-
In Cuba, where blackouts last for hours and charging an electric tricycle takes 10 hours with no guarantee of power, an entrepreneur inaugurated the country’s first free solar charging station; residents are already coming from 70 kilometers away just to get power.
-
Goodbye allergy and fine dust: Xiaomi launches purifier that removes 99.99% of particles in one hour, eliminates formaldehyde in two hours, reduces 98.9% of pollen, and delivers 11,666 liters of clean air per minute
-
Comet 3I/ATLAS comes from outside the Solar System, carries “heavy” water at an unprecedented level, and leaves scientists intrigued about where this alien visitor truly originated.
Development of the Tool
The project is led by Jan-Hendrik Ewers, a doctoral student at the James Watt School of Engineering at the University of Glasgow. According to him, the inspiration came from direct contact with reality. “I grew up in the rural Highlands and love hiking in the mountains, so I am fully aware of how dangerous hiking can be and of the incredible work that search and rescue teams do.,” he says.
Ewers explains that the initial goal of his doctorate was to test the use of machine learning to predict disappearance locations. However, he encountered an obstacle: the scarcity of data. Search teams prioritize saving lives, not collecting detailed records.
In light of this, researchers sought historical studies that analyzed the behavior of missing persons. Based on these studies, they were able to program the simulated agents and generate consistent results.
Statistical Heat Map
One of the most important aspects of the technology is the creation of a heat map. This map shows the areas with the highest probability of locating missing individuals. The team tested the system in a simulation on the Isle of Arran, located off the west coast of Scotland.
By releasing simulated agents at various points on the island, it was possible to compare the generated map with real data. The match between the predictions and real-world records surprised scientists. The result suggests that the digital agents reacted very similarly to real people.
Global Application
For David Anderson, a professor at the same engineering school and co-author of the study, the system could have global applications. “One of the advantages of this type of psychological modeling approach to locating missing persons is that it can potentially be applied to any landscape,” he asserts.
Additionally, the system can operate with drones. With appropriate sensors, drones can scan the areas indicated by the heat map, making searches more precise and faster. This represents a significant advancement for rescue teams, which often work with limited resources.
Promising Future of the New AI System
Ewers emphasizes that more testing is still necessary before applying the system in real operations. However, he believes the study represents a solid foundation for developing new practices.
“We are excited to explore the possibility of applying this technique to our ongoing efforts to harness the full potential of drones in search and rescue missions,” he said.
Even in its early stages, the technology shows that the combination of behavioral data and artificial intelligence can transform how missing persons are located. The study paves the way for a future where technology can be a decisive ally in critical situations.
With information from Interesting Engineering.
Be the first to react!