Keystroke dynamics study the way in which users input text via their keyboards. Having the ability to differentiate users, typing behaviors can unobtrusively form a component of a behavioral biometric recognition system to improve existing account security. Keystroke dynamics systems on free-text data have previously required 500 or more characters to achieve reasonable performance. In this paper, we propose a novel instance-based graph comparison algorithm called the instance-based tail area density (ITAD) metric to reduce the number of keystrokes required to authenticate users. Additionally, commonly used features in the keystroke dynamics literature, such as monographs and digraphs, are all found to be useful in informing who is typing. The usefulness of these features for authentication is determined using a random forest classifier and validated across two publicly available datasets. Scores from the individual features are fused to form a single matching score. With the fused matching score and our ITAD metric, we achieve equal error rates (EERs) for 100 and 200 testing digraphs of 9.7% and 7.8% for the Clarkson II dataset, improving upon state-of-the-art of 35.3% and 15.3%.

We consider a wireless sensor network for distributed estimation over fading channels. The sensors transmit their observations over a multiple access fading channel to a fusion center (FC), where a source parameter is estimated. The sensor transmissions add incoherently over a multiple access channel, which motivates the need for channel knowledge at the sensors to improve performance. We consider the effects of different fading channel models on the performance of the system, and characterize the effect of different amounts of channel information at the sensors. We calculate the variance of the estimate for cases when both perfect, and differing amounts of partial channel information are available at the sensors. Asymptotic variance expressions for large number of sensors are derived for different channel statistics and feedback scenarios. We show that the degradation in variance due to using only channel phase information is at most a factor of 4/¿ over Rayleigh fading channels. We consider continuous feedback error and evaluate the degradation in performance due to differing degrees of error. The loss in performance due to feedback quantization, and effect of error in feedback are also quantified. We also consider speed of convergence, and compare the rate of convergence under different conditions. Further, we characterize the effect of correlated channels between sensors and the FC, and provide the different values for the speed of convergence for this case. Simulation results are provided to show that only a few tens of sensors are required for the asymptotic results to hold. Numerical results corroborate our analytical results.

A distributed detection problem over fading Gaussian multiple-access channels is considered. Sensors observe a phenomenon and transmit their observations to a fusion center using the amplify and forward scheme. The fusion center has multiple antennas with different channel models considered between the sensors and the fusion center, and different cases of channel state information are assumed at the sensors. The performance is evaluated in terms of the error exponent for each of these cases, where the effect of multiple antennas at the fusion center is studied. When there is channel information at the sensors, the gain in error exponent due to having multiple antennas at the fusion center is shown to be limited to a factor of 8/π for Rayleigh fading channels between the sensors and the fusion center, and independent of the number of antennas at the fusion center. Simple practical schemes and numerical methods using semidefinite relaxation techniques are presented that utilize the limited possible gains available. Simulations are used to establish the accuracy of the results.

A sensor network is used for distributed signal-to-noise ratio (SNR) estimation in a single-time snapshot. Sensors observe a signal embedded in noise, and each observation is phase modulated using a constant-modulus scheme and transmitted over a Gaussian multiple-access channel to a fusion center. At the fusion center, the mean and variance are estimated jointly, using an asymptotically minimum-variance estimator. It is shown that this joint estimator decouples into simple individual estimators of the mean and the variance. The constant-modulus phase modulation scheme ensures a fixed transmit power, robust estimation across several sensing noise distributions, as well as an SNR estimate that requires a single set of transmissions from the sensors to the fusion center. The estimators are evaluated in terms of asymptotic variance, which are then used to evaluate the performance of the SNR estimator with Gaussian and Cauchy sensing noise distributions in the cases of total transmit power constraint as well as a per-sensor power constraint. For each sensing noise distribution, the optimal phase transmission parameters are also determined. The asymptotic relative efficiency of the estimators is evaluated. It is shown that among the noise distributions considered, the estimators are asymptotically efficient only when the noise distribution is Gaussian. Simulation results corroborate analytical results.

We consider a distributed detection problem over fading multiple-access channels. Sensors observe a phenomenon and transmit their observations to a fusion center using the amplify-and-forward scheme. The fusion center has multiple antennas and uses the transmissions from the sensors to run a detection algorithm. The channels are Ricean fading, and the sensors have no channel information. The performance is evaluated in terms of error exponent and compared with the AWGN channels case. The benefit of having multiple antennas at the fusion center is also quantified.