CPPS	Cyber-physical production system
IIoT	Industrial Internet of Things
RFID	Radio Frequency IDentification
BoM	Bill of Materials
IPS	Indoor positioning system
UWB	Ultra-Wide Band
BLE	Bluetooth Low Energy
MSDF	Multi-sensor data fusion
AoA	Angle of Arrival
SS	Signal Strength
RSS	Received Signal Strength
ToA	Time of Arrival
$p_1,\dots ,p_{N_p}$	products
$m_1,\dots ,m_{N_m}$	modules
$a_1,\dots ,a_{N_a}$	activities
$c_1,\dots ,c_{N_c}$	components
$w_1,\dots ,w_{N_w}$	workstations
$t_1,\dots ,t_{N_t}$	activity types
$\mathbf{A}$	($N_p\times N_a$) activities required to produce a product
$\mathbf{W}$	($N_a\times N_w$) workstation assigned for an activity
$\mathbf{B}$	($N_p\times N_c$) component/part required to produce a product
$\mathbf{P}$	($N_p\times N_p$) module/part family required to produce a product
$\mathbf{C}$	($N_a\times N_c$) component/part built in or processed in an activity
$\mathbf{M}$	($N_a\times N_m$) activity required to produce a module
$\mathbf{T}$	($N_a\times N_t$) category of the activity
${\mathbf{S}}^w$	($N_a\times l_w$) activity involved over a measured time interval
k	index of the production cycle (discrete time)
${\widehat{y}}_i^w\left(k\right)$	estimation of the individual activity times for work station w in the kth production cycle
${\mathbf{x}}^w\left(k\right)$	’efficiency’ of the operator, the vector of the estimated local activity times
$\mathbf{x}\left(k\right)$	workstation-independent version of ${\mathbf{x}}^w\left(k\right)$
$\mathbf{s}\left(k\right)$	sequence of the timestamps recorded by the active fixture sensors
${\mathbf{z}}^w\left(k\right)$	vector of the sum of the activity times that are situated between the two sensors
$\alpha$	index of the first sensor of a fixture-sensor pair
$\beta$	index of the second sensor of a fixture-sensor pair
${\mathbf{q}}_a$	the set of activities required to produce a specific product
${\mathbf{e}}^w$	serially uncorrelated white-noise vector of observational errors
${\mathbf{R}}^w\left(k\right)$	covariance matrix of observational errors
$\mathbf{H}\left(k\right)$	time-variable regressors representing the number of activities and built in components
$\mathbf{e}\left(k\right)$	the set of the serially uncorrelated white-noise vector of observational errors of the workstations
$\widehat{\mathbf{x}}\left(N\right)$	estimation error
$\mathbf{Q}$	positive-definite weighting matrix defined as $\mathbf{Q}={\left(\mathbf{R}\right)}^{-1}$
${\mathbf{P}}^{*}$	inverse of the parameter covariance matrix
${\mathbf{A}}^{*}\left(k\right)$	State-transition matrix in the Kalman filter represented estimation problem (in our case an identity matrix)
$\mathbf{K}\left(k\right)$	Gain of the Kalman filter/recursive estimator
${\mathbf{L}}^w$,${\mathbf{c}}^w$	Representation of the linear inequality constraints
${\mathbf{A}}_e^w$,${\mathbf{b}}_e^w$	Representation of the linear equality constraints
${\mu }_j$	vector of Lagrange multiplier associated with equality
${\lambda }_j$	vector of Lagrange multiplier associated with inequality constraints