According　to　the　portable　and　real-time　problems　on　the　driving　fatigue　prevention　based　on　electroencephalogram　(EEG),　a　headband　integrated　with　Thinkgear　EEG　chip,　tri-axial　accelerometer,　gyroscope　and　Bluetooth　is　developed　to　collect　the　subject＇s　left　prefrontal　Attention,　Meditation　EEG　and　head　movement　data.　The　relation　between　Attention　and　Meditation　EEG　when　the　subject　is　in　the　state　of　concentration,　relaxation,　fatigue　and　sleep　is　analyzed　firstly.　As　a　result,　a　new　method　for　driving　fatigue　detection　based　on　the　correlation　coefficient　between　subject＇s　Attention　and　Meditation　EEG　is　proposed.　Meanwhile,　the　slide　windows　and　k-Nearest　Neighbors　(k-NN)　algorithm　are　introduced　to　classify　the　correlation　coefficient　between　the　subject＇s　Attention　and　Meditation　EEG,　so　as　to　detect　driving　fatigue　and　alert.　Lastly,　a　software　running　on　an　Android　smart　device　is　developed　based　on　the　above　technologies,　and　the　experiment　proves　that　it　has　noninvasive　and　real-time　advantages,　while　its　sensitivity　and　specificity　are　80.98　%　and　90.43　%　respectively.