Table 1.

Comparison between annotated (human) and jaw sensor-determined sucking counts, including errors for breast-fed and bottle-fed infants during the epochs and the course of the meal.

Infant k	Feeding mode	Human counted sucks	Sensor- determined sucks	Human - annotated mean sucking count (per-epoch)	Sensor- determined mean sucking count (per-epoch)	Per-epoch mean count error $E_{EPOCH}^{CNT}(k)$ (%)	Per-meal mean count error ECNT (k) (%)	Threshold (T) (Volts)
1	Breast-fed	354	250	7.68	5.43	8.88	29.38	3.18
2	Breast-fed	774	701	8.70	7.88	−10.07	9.43	2.65
3	Breast-fed	859	946	9.76	10.74	−9.55	−10.13	0.39
4	Breast-fed	979	748	12.39	9.47	18.53	23.60	1.69
5	Breast-fed	329	263	10.27	8.20	16.65	20.06	1.53
6	Breast-fed	641	696	7.17	9.95	−15.15	−8.58	0.68
7	Bottle-fed	416	577	10.02	12.61	−40.95	−38.70	0.24
8	Bottle-fed	662	833	13.12	14.15	−36.61	−25.83	0.13
9	Bottle-fed	1023	1104	10.57	12.17	−14.61	−7.92	0.15
10	Bottle-fed	603	694	7.28	7.90	−14.29	−15.09	0.25
					Mean:	−9.72	−2.38	1.08
					STD:	20.03	22.33	1.11
					Absolute Mean:	18.52	18.87
					Absolute STD:	11.17	10.44

Note: k represents infant number in the dataset. Per-epoch mean sucking count for infant k was computed by dividing total sucking count by the number of epochs.