Blood Pressure Classification Using the Method of the Modular Neural Networks

Table 5

Classification for MNN with train method (traincsg).

No. Persons	Number of Neurons	Time	Systolic	Diastolic	Pulse	Classification
Person1	26,29	00:07:12	116	72	67	Optimal
Person 2	26,29	00:07:12	106	72	77	Optimal
Person 3	26,29	00:07:12	114	70	80	Optimal
Person 4	26,29	00:07:12	119	71	72	Optimal
Person 5	26,29	00:07:12	145	84	75	Grade1 Hypertension
Person 6	26,29	00:07:12	107	61	90	Normal
Person 7	26,29	00:07:12	130	87	97	High Normal
Person 8	26,29	00:07:12	120	64	97	Optimal
Person 9	26,29	00:07:12	131	74	73	High Normal
Person 10	26,29	00:07:12	122	78	57	Normal
Person 11	26,29	00:07:12	136	63	65	High Normal
Person 12	26,29	00:07:12	135	75	70	High Normal
Person 13	26,29	00:07:12	120	75	78	Normal
Person14	26,29	00:07:12	117	72	77	Optimal
Person 15	26,29	00:07:12	121	69	70	Normal
Person 16	26,29	00:07:12	132	90	78	High Normal
Person 17	26,29	00:07:12	126	76	80	Normal
Person 18	26,29	00:07:12	106	65	82	Optimal
Person 19	26,29	00:07:12	110	68	84	Optimal
Person 20	26,29	00:07:12	123	76	90	Normal
Person 21	26,29	00:07:12	112	71	78	Optimal
Person 22	26,29	00:07:12	111	70	70	Optimal
Person 23	26,29	00:07:12	122	73	71	Normal
Person 24	26,29	00:07:12	116	67	80	Optimal
Person 25	26,29	00:07:12	120	74	80	Optimal
Person 26	26,29	00:07:12	129	80	79	Normal
Person 27	26,29	00:07:12	120	61	74	Optimal
Person 28	26,29	00:07:12	112	73	81	Optimal
Person 29	26,29	00:07:12	121	82	67	Normal
Person 30	26,29	00:07:12	95	61	77	Optimal
Person 31	26,29	00:07:12	106	65	80	Optimal
Person 32	26,29	00:07:12	116	75	72	Optimal
Person 33	26,29	00:07:12	116	71	75	Normal
Person 34	26,29	00:07:12	130	86	90	Normal
Person 35	26,29	00:07:12	117	74	97	Optimal
Person 36	26,29	00:07:12	117	58	88	Optimal
Person 37	26,29	00:07:12	113	70	73	Optimal
Person 38	26,29	00:07:12	131	71	80	Normal
Person 39	26,29	00:07:12	128	81	82	Normal
Person 40	26,29	00:07:12	134	85	81	Normal