Driving　fatigue　is　one　of　the　main　causes　of　traffic　accidents　in　monotonous　environments　such　as　grassland　highways.　However,　the　process　of　generation　of　driving　fatigue　on　grassland　highways　is　still　not　clear.　A　driving　simulation　experiment　with　23　participants　was　performed　to　collect　data　on　driving　behavior,　reaction　time　and　electrocardiogram　(ECG)　results　when　driving　on　a　grassland　highway.　The　effective　feature　indicators　of　driving　fatigue　based　on　driving　behavior　data　were　calculated　by　Pearson　correlation　coefficient　and　principal　component　analysis　method.　The　matter-element　model　based　on　entropy　weight　method　was　used　to　quantify　the　generation　process　of　driving　fatigue　(GPDF).　GPDF　was　classified　as　different　patterns　by　the　eigenvalue　of　GPDF　curves.　Reaction　time　and　ECG　data　were　utilized　to　verify　the　rationality　of　GPDF.　Results　show　that　there　were　13　feature　indicators　of　driving　behavior　suitable　for　driving　fatigue　description.　GPDF　was　not　completely　consistent　among　different　participants　and　was　classified　into　three　patterns　(i.e.,　mild,　moderate　and　severe　fatigue).　The　mean　similarity　for　GPDF　in　each　pattern　was　0.87,　0.61　and　0.50.　Validation　test　demonstrated　that　driving　fatigue　detection　accuracy　by　GPDF　was　72%.　The　mean　similarity　of　the　GPDF　between　driving　behavior　and　ECG　was　0.72.　Driving　fatigue　tended　to　occur　with　driving　time　of　19　min　or　33　min.　This　study　is　helpful　to　understand　GPDF　on　grassland　highways　from　the　perspective　of　individual　driving　behavior,　which　would　provide　suggestions　for　the　reasonable　setting　of　anti-fatigue　devices.