This paper proposes the novel Alzheimer dementia (AD) detection method based on unstable circadian rhythm of heartrate acquired from mattress sensor. Concretely, the pro-posed method, UCRADD (Unstable Circadian Rhythm based Alzheimer Dementia Detection), estimates the circadian rhythm of heartrate by calculating the regression of the trigonometric functions with the maximum likelihood estimation, and judges instability of the circadian rhythm by the coefficients of the equation estimated trigonometric functions. Through the human subject experiment with one elderly AD subject in two months (i.e., August and December), three elderly (age from 60-70) non-AD subjects, the ten middle-aged non-AD subjects and eight young non-AD subjects, the following implications have been revealed: (1) UCRADD succeeds to detect the AD patients in the high rate and keeps it in two months (78.9% in August and 82.4% in December), while our previous method cannot keep the rate at the same level in two months (57.9% in August and 82.4% in December). (2) the instability of circadian rhythm of heartrate has the potential of being new symptom of AD.