Method for distinguishing high and low floors based on LTE signal
A low-floor and floor-level technology, applied in the field of high-low-floor distinction, can solve problems such as the large impact of floor recognition accuracy and signal strength fluctuations
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0075] Specific implementation mode one: combine figure 1 , image 3 , Figure 4 The present embodiment is described, and the method for distinguishing high and low floors based on LTE signals provided in this embodiment specifically includes the following steps:
[0076] Step 1. Select the coordinate origin P0(X 0 ,Y 0 ,Z 0 ), and establish a building-level three-dimensional Cartesian coordinate system P0XY Z; such as figure 1 shown.
[0077] Step 2, on each floor, according to the indoor environment of this floor, evenly select some reference points, carry out LTE signal acquisition at the reference points by a platform carrying LTE signal acquisition equipment (such as a mobile phone), and record the obtained LTE signals floor information in
[0078] Step 3. Obtain the reference signal received power RSRP, LTE reference signal received quality RSRQ, received signal strength indicator RSSI, Evolved UTRAN cell identity ECI, and neighboring cell RSRP of the primary serv...
specific Embodiment approach 2
[0081] Specific embodiment two: the difference between this embodiment and specific embodiment one is that the establishment of offline database Database described in step 3 specifically includes the following steps:
[0082] Step 31. Calculate the set of all ECIs in the collected LTE signal; set the set of all cells in the i-th LTE signal as {ECI} i , the total number of collected LTE signals is m, i=1,2,...,m; the set ECI of all ECI all for:
[0083]
[0084] Among them, N is the number of ECI; ECI j for ECI all The j-th ECI in ; j=1,2,...,N;
[0085] Step 32. To the RSRP value of the j-th cell in the i-th LTE signal Do the following:
[0086]
[0087] Wherein, RSRP_L is a fixed value smaller than the RSRP value in all collected LTE signals;
[0088] Step 33, through the process of step 32, obtain the RSRP matrix:
[0089]
[0090] Construct the RSSI vector:
[0091] RI=[RI 1 RI 2 … RI m ] T (4)
[0092] Among them, RI i is the RSSI of the primary ...
specific Embodiment approach 3
[0104] Specific embodiment three: the difference between this embodiment and specific embodiment two is that step 4 uses the support vector machine algorithm to train the offline database Database to obtain the floor recognition model, which specifically includes the following steps:
[0105] Step 41. Divide the Database into two categories according to the height of the floors: high floors and low floors;
[0106] Step 42. Determine the objective function:
[0107]
[0108] in, is the transpose of the i-th row of the signal space S in the offline database Database, l i is the i-th component of the position vector in the offline database Database; and is the variable to be optimized; represents a real number, Represents a real number matrix with N+2 rows and 1 column;
[0109] Step 43. Define the Lagrange function:
[0110]
[0111] Among them, α=[α 1 ,α 2 ,…,α m ] T , α i is the Lagrange multiplier, and α i ≥0,i=1,2,…,m; transform the objective functio...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More