Prognoses of Traumatic Brain Injury (TBI) outcomes are neither easily nor accurately determined from clinical indicators. This is due in part to the heterogeneity of damage inflicted to the brain, ultimately resulting in diverse and complex outcomes. Using a data-driven approach on many distinct data elements may be necessary to describe this large set of outcomes and thereby robustly depict the nuanced differences among TBI patients' recovery. In this work, we develop a method for modeling large heterogeneous data types relevant to TBI. Our approach is geared toward the probabilistic representation of mixed continuous and discrete variables with missing values. The model is trained on a dataset encompassing a variety of data types, including demographics, blood-based biomarkers, and imaging findings. In addition, it includes a set of clinical outcome assessments at 3, 6, and 12 months post-injury. The model is used to stratify patients into distinct groups in an unsupervised learning setting. We use the model to infer outcomes using input data, and show that the collection of input data reduces uncertainty of outcomes over a baseline approach. In addition, we quantify the performance of a likelihood scoring technique that can be used to self-evaluate the extrapolation risk of prognosis on unseen patients.

In this paper, we address the multiple sound source localization problem by associating and fusing the direction of arrival (DOA) estimates from multiple microphone arrays. For multi-source scenarios especially in indoor environments, a critical issue is to tell the correspondence among DOA estimates across different arrays, which is known as the data association problem. We propose a multi-dimensional assignment-based data association approach to find the optimal associations of DOA estimates from the same source. First, in the sense of maximum likelihood, the data association problem is formulated by finding the most likely partition of the measurement set into the source-originated and false alarm-originated subsets. Next, by defining the association costs appropriately, the problem of finding the most likely measurement partition is transformed into a generalized multi-dimensional assignment problem which can be solved efficiently by a Lagrangian relaxation algorithm. After the optimal associations of DOA estimates across different arrays are obtained, the locations of sources can be estimated by fusing the same source-originated DOA estimates. In the presence of missed detections, false alarms and the unknown number of sources, the proposed method achieves high accuracy in data association and localization, and outperforms the competing method in reverberant and noisy environments. In addition, since our method does not require additional features and uses DOA estimates only, it is more computationally efficient than the competing method.

In this paper, we address the multiple sound source localization problem using time differences of arrival (TDOAs) of sound sources to a microphone array. Typically, TDOAs are estimated based on the peak extraction of the generalized crosscorrelation function. In multi-source cases, for any given microphone pair, it is hard to tell the correspondence between the sound sources and the extracted peaks. In this work, we develop a novel localization approach based on data association which combines multiple TDOAs from the same source across different microphone pairs. Firstly, the generalized cross correlation-phase transform (GCC-PHAT) function is evaluated and multiple peaks of the GCC function indicating candidate TDOAs are extracted for each pair of microphones. Next, we employ the multi-dimensional assignment algorithm to associate multiple TDOAs from the same source. Finally, multiple sound source localization is carried out based on the obtained TDOA associations across different microphone pairs. Experimental results show the proposed method achieves superior performance for multiple sound source localization compared to the competing algorithm, especially in noisy environments.

Obstructive sleep apnea (OSA) is a chronic sleep disorder affecting millions of people worldwide. Individuals with OSA are rarely aware of the condition and are often left untreated, which can lead to some serious health problems. Nowadays, several low-cost wearable health sensors are available that can be used to conveniently and noninvasively collect a wide range of physiological signals. In this paper, we propose a new framework for OSA detection in which we combine the wearable sensor measurement signals with the mathematical models of the cardiorespiratory system. Vector-valued Gaussian processes (GPs) are adopted to model the physiological variations among different individuals. The GP covariance is constructed using the sum of separable kernel functions, and the GP hyperparameters are estimated by maximizing the marginal likelihood function. A likelihood ratio test is proposed to detect OSA using the widely available heart rate and peripheral oxygen saturation (SpO ) measurement signals. We conduct experiments on both synthetic and real data to show the effectiveness of the proposed OSA detection framework compared to purely data-driven approaches.

In this paper, we consider the source localization problem in which several microphones collaborate to locate an active sound source in a reverberant environment. Sound source localization (SSL) based on the Generalized Cross Correlation (GCC) function is widely studied for the past few decades. However, in a reverberant environment, the maximal peak of the GCC function does not necessarily correspond to the true source location due to the multipath effect. In this case, the traditional GCC-based method performs poorly. In this paper, by combining the information from all the available microphone pairs, we aim to seek a set of source-originated peaks rather than the maximal peaks. To achieve this, for each pair of microphones, multiple peaks of the GCC function indicating candidate TDOAs are extracted firstly. A graphic model is then constructed based on the extracted TDOAs from multiple microphone pairs, and the optimal association of peaks corresponding to true time delays can be obtained by optimizing the association cost function for the given set of peaks. Finally, the source location is estimated in the least square sense. Simulation results show the superior performance of the proposed approach compared with the traditional GCC-based localization algorithm.

This paper deals with sound source localization and number estimation in indoor environments using a circular microphone array. Multiple sound source localization is achieved by performing single source localization at each selected time-frequency (TF) point of received signals after short-time Fourier transform. A TF point selection method is proposed to reduce the computational time, which depends on a trained SVM with power and power ratio of TF points as its features. Nonparametric Bayesian clustering is applied on the obtained DOA estimates to identify the number of active sources. The algorithm is shown to outperform others through simulations.

Traditional biometric recognition systems often utilize physiological traits such as fingerprint, face, iris, etc. Recent years have seen a growing interest in electrocardiogram (ECG)-based biometric recognition techniques, especially in the field of clinical medicine. In existing ECG-based biometric recognition methods, feature extraction and classifier design are usually performed separately. In this paper, a multitask learning approach is proposed, in which feature extraction and classifier design are carried out simultaneously. Weights are assigned to the features within the kernel of each task. We decompose the matrix consisting of all the feature weights into sparse and low-rank components. The sparse component determines the features that are relevant to identify each individual, and the low-rank component determines the common feature subspace that is relevant to identify all the subjects. A fast optimization algorithm is developed, which requires only the first-order information. The performance of the proposed approach is demonstrated through experiments using the MIT-BIH Normal Sinus Rhythm database.

This paper introduces an online sleep apnea detection method based on heart rate complexity as measured by recurrence quantification analysis (RQA) statistics of heart rate variability (HRV) data. RQA statistics can capture nonlinear dynamics of a complex cardiorespiratory system during obstructive sleep apnea. In order to obtain a more robust measurement of the nonstationarity of the cardiorespiratory system, we use different fixed amount of neighbor thresholdings for recurrence plot calculation. We integrate a feature selection algorithm based on conditional mutual information to select the most informative RQA features for classification, and hence, to speed up the real-time classification process without degrading the performance of the system. Two types of binary classifiers, i.e., support vector machine and neural network, are used to differentiate apnea from normal sleep. A soft decision fusion rule is developed to combine the results of these classifiers in order to improve the classification performance of the whole system. Experimental results show that our proposed method achieves better classification results compared with the previous recurrence analysis-based approach. We also show that our method is flexible and a strong candidate for a real efficient sleep apnea detection system.

Detecting and reconstructing critical dynamic event regions at a control center is an important application of bandwidth-limited wireless sensor networks (WSNs). In this paper, the problem of adaptive bandwidth allocation for sensor data collection is studied. The spatiotemporal relationship of the evolving field is assumed and modeled by dynamic Markov random fields. Observations are collected from a network of sensors distributed in the field. To meet the stringent bandwidth and energy constraints in WSNs, only a few selected sensors are allowed to transmit compressed data to a control center. To reconstruct and track the field state map at each time step, a processing framework including sensor selection and local and central processing is proposed. Specifically, adaptive bandwidth allocation is obtained by solving a conditional entropy-based optimization problem. Mean-field approximation with incomplete quantized sensor observations is carried out at the center for dynamic event region detection. The overall communication costs in terms of the bandwidth and energy consumption of the proposed framework are evaluated by considering all possible overheads in a practical communication protocol. The performance is analyzed through simulations, and the effectiveness and efficiency are demonstrated by comparing with other methods.

Semantic information can help both humans and robots to understand their environments better. In order to obtain semantic information efficiently and link it to a metric map, we present a semantic mapping approach through human activity recognition in an indoor human-robot coexisting environment. An intelligent mobile robot platform can create a 2D metric map, while human activity can be recognized using motion data from wearable motion sensors mounted on a human subject. Combined with pre-learned models of activity-to-furniture type association and robot pose estimates, the robot can determine the distribution of the furniture types on the 2D metric map. Simulations and real world experiments demonstrate that the proposed method is able to create a reliable metric map with accurate semantic information.

The concept of cognitive radio with many promising features like spectrum sensing, dynamic spectrum access has the potential to greatly improve the spectral efficiency. In this paper, we consider the problem of spectrum-hole sharing, i.e., vacant channel and power allocation to multiple cognitive radio (CR) users who coexist in a network. These CR users are equipped with multiple antennas at both transmitters and receivers. A non-cooperative game with pricing formulation is adopted to tackle the problem. We show that, to achieve the maximum sum data rate, each user should incorporate a vector of adaptive pricing factors on each channel based on transmission power of other users. The formula of optimal pricing is derived and a distributed iterative algorithm is designed through small amount of information exchange between users. The simulation results demonstrate the performance gain of the proposed algorithm over the classical iterative water-filling algorithm without pricing and intuitive pricing formulations.

In this paper, we study one-bit quantizer design for distributed estimation under the minimax criterion for wireless sensor network (WSN) applications. Identical local quantizers are generally difficult to design because of the dependence on the unknown parameter under estimation. Nonidentical local quantizers are more robust in that sense. However, its design generally involves multi-dimensional optimization, which is computationally complex and the complexity increases with the number of sensors in the WSN. By studying the optimal nonidentical quantizers of M sensors, two quantizer structures are proposed. One is the sinusoid function, i.e., the quantization thresholds at M sensors follow a sinusoid function. The other is the more general raised cosine function, which requires two-dimensional optimization. The Nelder-Mead optimization method is adopted, which is simplex-based search directly using objective function values. Simulation results show that the quantizers with proposed structures outperform the intuitive uniform quantizer design. The raised cosine structure achieves near optimal performance.

The problem of distributed estimation of an unknown parameter in noise is considered. Sensor observations are compressed using a one-bit quantizer and then transmitted to a fusion center over fading channels. We propose a mean estimator which requires only the knowledge of the mean of the channel gain and a sign estimator where the signs of the received signals are used for parameter estimation. Our analysis shows that these two estimators are not only computationally efficient, but also achieve comparable performance of maximum likelihood estimation. A robust iterative algorithm is proposed to address the design issue of local quantization thresholds.

In this paper, the problem of event-region detection in wireless sensor networks (WSNs) are explored. Sensor fusion techniques are developed to tackle this problem. However, in contrast to the existing sensor fusion rules in the literature, sensor nodes considered here could observe different phenomena or events, and each node makes its decision with respect to its own hypothesis. In particular, a space-memory fusion rule that considers both space-memory information and local detection performance is derived for event-region detection. In addition, the proposed fusion rule performs in a sequential manner. The need of the fault-tolerance capability for possible sensor faults is also integrated with the design of the space-memory fusion rule. Specifically, the a priori sensor-fault model is used in this paper to address the issue of fault-tolerance capability. Simulation results demonstrate the superiority of the proposed fusion rule in the event-region detection.

Feature selection is a key task in remote sensing data processing, particularly in case of classification from hyperspectral images. A logistic regression (LR) model may be used to predict the probabilities of the classes on the basis of the input features, after ranking them according to their relative importance. In this letter, the LR model is applied for both the feature selection and the classification of remotely sensed images, where more informative soft classifications are produced naturally. The results indicate that, with fewer restrictive assumptions, the LR model is able to reduce the features substantially without any significant decrease in the classification accuracy of both the soft and hard classifications.

Existing studies on the classical distributed detection problem typically assume idealized transmissions between local sensors and a fusion center. This is not guaranteed in the emerging wireless sensor networks with low-cost sensors and stringent power/delay constraints. By focusing on discrete transmission channels, we study the performance limits, in both asymptotic and non-asymptotic regimes, of a distributed detection system as a function of channel characteristics. For asymptotic analysis, we compute the error exponents of the underlying hypothesis testing problem; while for cases with a finite number of sensors, we determine channel conditions under which the distributed detection systems become useless - observing the channel outputs cannot help reduce the error probability at the fusion center. We demonstrate that as the number of sensors or the quantization levels at local sensors increase, the requirements on channel quality can be relaxed

The problem of distributed sequential detection in the presence of communication constraints is considered. The observations available at each sensor are first compressed to multibit sensor decisions and sent to the fusion center. At the fusion center, a sequential data fusion scheme is implemented in order to reach a global decision. An algorithm is developed for optimal bandwidth distribution among sensors under a fixed bandwidth constraint. Under symmetry and conditional independence assumptions, the algorithm can be simplified substantially: the cooperative quantizer design algorithm reduces to independent quantizer design. The case when communication bandwidth is the only constraint is also considered.