The　Android　smartphone,　with　its　open　source　character　and　excellent　performance,　has　attracted　many　users.　However,　the　convenience　of　the　Android　platform　also　has　motivated　the　development　of　malware.　The　traditional　method　which　detects　the　malware　based　on　the　signature　is　unable　to　detect　unknown　applications.　The　article　proposes　a　machine　learning-based　lightweight　system　that　is　capable　of　identifying　malware　on　Android　devices.　In　this　system　we　extract　features　based　on　the　static　analysis　and　the　dynamitic　analysis,　then　a　new　feature　selection　approach　based　on　principle　component　analysis　(PCA)　and　relief　are　presented　in　the　article　to　decrease　the　dimensions　of　the　features.　After　that,　a　model　will　be　constructed　with　support　vector　machine　(SVM)　for　classification.　Experimental　results　show　that　our　system　provides　an　effective　method　in　Android　malware　detection.