ABSTRACT
This paper proposes a channel state information (CSI)-based prediction method of a human flow that includes activity. The objective of the paper is to predict a human flow in an outdoor road. This human flow prediction is useful for the prediction of the number of passing people and their activity without privacy issues as a result of the absence of any camera systems. In this paper, we assume seven types of activities: one, two, and three people walking; one, two, and three people running; and one person cycling. Since the CSI can effectively express the effect of multipath fading in wireless signals, we expected the CSI to predict the various activities. In our proposed method, the amplitude and phase components are extracted from the measured CSI. The feature values for machine learning are the mean and variance of the maximum eigenvalue derived from the auto-correlation matrix and variance-covariance matrix composed of the amplitude or phase components and the passing time of flow. Using these feature values, we evaluated the prediction accuracy by leave-one-out cross-validation with a linear support vector machine (SVM). As a result, the proposed method achieved the maximum prediction accuracy of 100% for each direction and 99.5% for two directions.
Subject(s)
Support Vector Machine , Wireless Technology , Bicycling , Humans , Running , WalkingABSTRACT
OBJECTIVES: In a cross-sectional study, we investigated renal function based on estimated glomerular filtration rate (eGFR) and urinary protein levels from Specific Health Examinations in Kitakyushu city related to risk factors for cardiovascular events and metabolic syndrome in residents. METHODS: For this study, 21,625 citizens (male/female=8,637/12,988) of Kitakyushu city were investigated. Citizens were enrolled in national health insurance and data were collected from a database classified for "Specific Health Guidance" by the Kokura Medical Association health testing and services center in 2010. RESULTS: As a whole, the stage of CKD increased with age, especially among those aged 70-74 years; 32% were at CKD stage 3. Only 11% of the CKD stage 3 group had a positive urinary protein (UP) test. Subjects in stages 3-5 CKD had a higher ratio of abdominal obesity, higher systolic and diastolic blood pressure, increased fasting blood glucose, HbA1c, and fasting triglyceride levels, and lower levels of HDL-C in comparison to subjects with CKD in stages 1-2. These factors increase the complication ratio of MetS for subjects in stages 3-5. The group with a history of stroke or heart disease had a significantly lower eGFR. CONCLUSION: There is a strong relationship between CKD and risk factors for cardiovascular events and MetS. It has been indicated that lifestyle modifications, suggested by primary care doctors, are very important for the early prevention of CKD. A new preventive CKD system in Kitakyushu city, based on a Specific Health Examination, began during the fiscal year 2011, and this system is expected to decrease the incidence of end-stage renal disease and cardiovascular events.
