Electrocardiogram　(ECG)　is　the　primary　basis　for　the　diagnosis　of　cardiovascular　diseases.　However,　the　amount　of　ECG　data　of　patients　makes　manual　interpretation　time-consuming　and　onerous.　Therefore,　the　intelligent　ECG　recognition　technology　is　an　important　means　to　decrease　the　shortage　of　medical　resources.　This　study　proposes　a　novel　classification　method　for　arrhythmia　that　uses　for　the　very　first　time　a　three-heartbeat　multi-lead　(THML)　ECG　data　in　which　each　fragment　contains　three　complete　heartbeat　processes　of　multiple　ECG　leads.　The　THML　ECG　data　pre-processing　method　is　formulated　which　makes　use　of　the　MIT-BIH　arrhythmia　database　as　training　samples.　Four　arrhythmia　classification　models　are　constructed　based　on　one-dimensional　convolutional　neural　network　(1D-CNN)　combined　with　a　priority　model　integrated　voting　method　to　optimize　the　integrated　classification　effect.　The　experiments　followed　the　recommended　inter-patient　scheme　of　the　Association　for　the　Advancement　of　Medical　Instrumentation　(AAMI)　recommendations,　and　the　practicability　and　effectiveness　of　THML　ECG　data　are　proved　with　ablation　experiments.　Results　show　that　the　average　accuracy　of　the　N,　V,　S,　F,　and　Q　classes　is　94.82%,　98.10%,　97.28%,　98.70%,　and　99.97%,　respectively,　with　the　positive　predictive　value　of　the　N,　V,　S,　and　F　classes　being　97.0%,　90.5%,　71.9%,　and　80.4%,　respectively.　Compared　with　current　studies,　the　THML　ECG　data　can　effectively　improve　the　morphological　integrity　and　time　continuity　of　ECG　information　and　the　1D-CNN　model　of　ECG　sequence　has　a　higher　accuracy　for　arrhythmia　classification.　The　proposed　method　alleviates　the　problem　of　insufficient　samples,　meets　the　needs　of　medical　ECG　interpretation　and　contributes　to　the　intelligent　dynamic　research　of　cardiac　disease.　©　2013　IEEE.