A framework for mining internet-of-things to solve complex problems /
Mohammed Anas Haroun
A framework for mining internet-of-things to solve complex problems / إطار للتنقب في انترنت الاشاء من اجل حل المسائل المعقدة Mohammed Anas Haroun ; Supervised Amr Ahmed Badr , Sherif Essam Eldin Khattab - Cairo : Mohammed Anas Haroun , 2017 - 103 Leaves : charts ; 30cm
Thesis (M.Sc.) - Cairo University - Faculty of Computers and Information - Department of Computer Science
One of Internet of things (IoT) big opportunities is the huge data that can be collected. As human heuristics have been shown to improve performance of complex problems and deliver more accurate results, IoT data can be used to extract these heuristics. In this thesis we present a framework to capture human heuristics from taxi drivers using data collected from sensors deployed in the taxis. The captured heuristics are used to create initial chromosomes for a genetic algorithm to solve the Travelling Salesman Problem (TSP). A dataset collected from 10,357 taxis in Beijing for 18 months was used. The quality of the TSP solutions was improved by up to 49% as compared to the same genetic algorithm with randomly initialized chromosomes. The results show a promising potential for augmenting heuristic search algorithms by data collected from the IoT
Internet of things Mining internet Solve complex problems
A framework for mining internet-of-things to solve complex problems / إطار للتنقب في انترنت الاشاء من اجل حل المسائل المعقدة Mohammed Anas Haroun ; Supervised Amr Ahmed Badr , Sherif Essam Eldin Khattab - Cairo : Mohammed Anas Haroun , 2017 - 103 Leaves : charts ; 30cm
Thesis (M.Sc.) - Cairo University - Faculty of Computers and Information - Department of Computer Science
One of Internet of things (IoT) big opportunities is the huge data that can be collected. As human heuristics have been shown to improve performance of complex problems and deliver more accurate results, IoT data can be used to extract these heuristics. In this thesis we present a framework to capture human heuristics from taxi drivers using data collected from sensors deployed in the taxis. The captured heuristics are used to create initial chromosomes for a genetic algorithm to solve the Travelling Salesman Problem (TSP). A dataset collected from 10,357 taxis in Beijing for 18 months was used. The quality of the TSP solutions was improved by up to 49% as compared to the same genetic algorithm with randomly initialized chromosomes. The results show a promising potential for augmenting heuristic search algorithms by data collected from the IoT
Internet of things Mining internet Solve complex problems