(a) 2D Emotion Model: EQ-Radio adopts a 2D emotion
model whose axes are valence and arousal; this model
serves as the most common approach for categorizing
human emotions in past literature. 26, 30 The model
classifies between four basic emotional states: Sadness
(negative valence and negative arousal), Anger (
negative valence and positive arousal), Pleasure (positive
valence and negative arousal), and Joy (positive valence
and positive arousal).
(b) Feature Extraction: EQ-Radio extracts features from
both the heartbeat sequence and the respiration signal. There is a large literature on extracting emotion-dependent features from human heartbeats, 3, 26, 36
where past techniques use on-body sensors. These
features can be divided into time-domain analysis,
frequency-domain analysis, time-frequency analysis,
Poincaré plot, 24 Sample Entropy, 28 and Detrend
Fluctuation Analysis. 34 EQ-Radio extracts 27 features
from IBI sequences as listed in Table 1. These particular features were chosen in accordance with the
results in Ref. Kim and André. 26 We refer the reader to
Ref. Acharya et al. 3; Ref. Kim and André. 26 for a detailed
explanation of these features.
EQ-Radio also employs respiration features. To
extract the irregularity of breathing, EQ-Radio first
identifies each breathing cycle by peak detection after
low pass filtering. Since past work that studies breathing features recommends time-domain features, 36
EQ-Radio extracts the time-domain features in the first
row of Table 1.
(c) Handling Dependence: Physiological features differ
from one subject to another for the same emotional
state. Further, those features could be different for
the same subject on different days. This is caused by
multiple factors, including caffeine intake, sleep, and
baseline mood of the day. In order to extract better
features that are user-independent and day-indepen-dent, EQ-Radio incorporates a baseline emotional
state: neutral. The idea is to leverage changes of physiological features instead of absolute values. Thus,
EQ-Radio calibrates the computed features by subtracting for each feature its corresponding values calculated at the neutral state for a given person on a
(d) Feature Selection and Classification: As mentioned
earlier, the literature has many features that relate
IBI to emotions. Using all of those features with a
The recursive relationship for the dynamic program is as fol-
lows: if Dt denotes the minimal cost of segmenting sequence
where tt,B specifies possible choices of t based on segment
length constraints. The time complexity of the dynamic program based on Equation 5 is O(n) and the global optimum is
Update template µ. In the l-th iteration, template µl+ 1 is
updated given segmentation Sl+ 1 as follows:
where m is the required length of template. The above opti-
mization problem is a weighted least squares with the fol-
lowing closed-form solution:
Figure 4 shows the final beat segmentation for the data in
Figure 3. The figure also shows the ECG data of the subject.
The segmented beat length matches the ECG of the subject
to within a few milliseconds. There is a small delay since
the ECG measures the electric signal of the heart, whereas
the RF signal captures the heart’s mechanical motion as it
reacts to the electric signal. 47
6. EMOTION CLASSIFICATION
After EQ-Radio recovers individual heartbeats from RF
reflections, it uses the heartbeat sequence along with the
breathing signal to recognize the person’s emotions.
.836 .804 .792 .824 .848 .828 .812 .840 .836
.832 .804 .792 .828 .840 .828 .816 .840 .840
Figure 4. Segmentation Result Compared to ECG. The figure shows
that the length of our segmented beats in RF (top) is very similar
to the length of the segmented beats in ECG (bottom). There is a
small delay since the ECG measures the electric signal of the heart,
whereas the RF signal captures the heart’s mechanical motion as it
reacts to the electric signal.
Selected IBI features in bold; selected respiration features in italic.
Table 1. Features used in EQ-Radio.
Time Mean, Median, SDNN, pNN50, RMSSD, SDNNi, meanRate,
Frequency Welch PSD: LF/HF, peakLF, peakHF. Burg PSD: LF/HF, peakLF,
peakHF. Lomb-Scargle PSD: LF/HF, peakLF, peakHF.
Poincaré SD1, SD2, SD2/SD1.
Nonlinear SampEn1, SampEn2, DFAall, DFA1, DFA2.