Estimating a sequence of dynamic undirected graphical models, in which adjacent graphs share similar structures, is of paramount importance in various social, financial, biological, and engineering systems, since the evolution of such networks can be utilized for example to spot trends, detect anomalies, predict vulnerability, and evaluate the impact of interventions. Existing methods for learning dynamic graphical models require the tuning parameters that control the graph sparsity and the temporal smoothness to be selected via brute-force grid search. Furthermore, these methods are computationally burdensome with time complexity O(NP3)O(NP3) for PP variables and NN time points. As a remedy, we propose a low-complexity tuning-free Bayesian approach, named BASS. Specifically, we impose temporally dependent spike and slab priors on the graphs such that they are sparse and varying smoothly across time. An efficient variational inference algorithm based on natural gradients is then derived to learn the graph structures from the data in an automatic manner. Owing to the pseudo-likelihood and the mean-field approximation, the time complexity of BASS is only O(NP2)O(NP2). To cope with the local maxima problem of variational inference, we resort to simulated annealing and propose a method based on bootstrapping of the observations to generate the annealing noise. We provide numerical evidence that BASS outperforms existing methods on synthetic data in terms of structure estimation, while being more efficient especially when the dimension PP becomes high. We further apply the approach to the stock return data of 78 banks from 2005 to 2013 and find that the number of edges in the financial network as a function of time contains three peaks, in coincidence with the 2008 global financial crisis and the two subsequent European debt crisis. On the other hand, by identifying the frequency-domain resemblance to the time-varying graphical models, we show that BASS can be extended to learning frequency-varying inverse spectral density matrices, and further yields graphical models for multivariate stationary time series. As an illustration, we analyze scalp EEG signals of patients at the early stages of Alzheimer's disease (AD) and show that the brain networks extracted by BASS can better distinguish between the patients and the healthy controls.

With the emergence of innovations associated with public transport (PT) services, such as Mobility-as-a-Service, demand responsive transit, and autonomous vehicles, the door-to-door PT journey is achievable via multiple transfers between and within different PT modes. As such, seamless transfers between different modes of public transportation become an increasingly important factor for the attractiveness of PT services. At the same time, recent developments in travel time prediction methodologies offer new, reliable data sources for the optimization of PT operations. This work, with the consideration of these two elements, develops a mixed integer linear programming model for the PT schedule synchronization problem. The novelty is threefold. First, a novel concept of path-oriented scheduling is proposed. The path transfer time is explicitly formulated and minimized to provide a seamless travel experience considering that the emerging multimodal mobility inevitably induces multiple transfers. Second, time-dependent travel time data is also utilized in the model, which allows us to harness new and more representative data sources for improving PT services. Third, in order to complement the increase in computational complexity as a result of the utilization of time-dependent travel time data, three novel valid inequalities (VIs) are derived. Numerical studies show that the use of time-dependent travel time data is beneficial in terms of reducing path transfer times, when compared to using the mean historical travel times. The numerical study also reveals a tradeoff between the maximum allowable path transfer time and trip time. Using simulation studies on three bus lines in Copenhagen, we demonstrate that the valid inequalities could reduce the computation time by 8.5% on average, where the maximum reduction of computation time could reach 54.0%. The proposed valid inequalities are benchmarked against two classes of valid inequalities in the literature. It is found that the proposed valid inequalities could outperform those in the literature. We also found that further improvement in computational performance can be attained by using a combination of the proposed valid inequalities.

We propose two end-to-end neural configurations for language diarization on bilingual code-switching speech. The first, a BLSTM-E2E architecture, includes a set of stacked bidirectional LSTMs to compute embeddings and incorporates the deep clustering loss to enforce grouping of languages belonging to the same class. The second, an XSA-E2E architecture, is based on an x-vector model followed by a self-attention encoder. The former encodes frame-level features into segmentlevel embeddings while the latter considers all those embeddings to generate a sequence of segment-level language labels. We evaluated the proposed methods on the dataset obtained from the shared task B in WSTCSMC 2020 and our handcrafted simulated data from the SEAME dataset. Experimental results show that our proposed XSA-E2E architecture achieved a relative improvement of 12.1% in equal error rate and a 7.4% relative improvement on accuracy compared with the baseline algorithm in the WSTCSMC 2020 dataset. Our proposed XSA-E2E architecture achieved an accuracy of 89.84% with a baseline of 85.60% on the simulated data derived from the SEAME dataset.

Epilepsy diagnosis based on Interictal Epileptiform Discharges (IEDs) in scalp electroencephalograms (EEGs) is laborious and often subjective. Therefore, it is necessary to build an effective IED detector and an automatic method to classify IED-free versus IED EEGs. In this study, we evaluate features that may provide reliable IED detection and EEG classification. Specifically, we investigate the IED detector based on convolutional neural network (ConvNet) with different input features (temporal, spectral, and wavelet features). We explore different ConvNet architectures and types, including 1D (one-dimensional) ConvNet, 2D (two-dimensional) ConvNet, and noise injection at various layers. We evaluate the EEG classification performance on five independent datasets. The 1D ConvNet with preprocessed full-frequency EEG signal and frequency bands (delta, theta, alpha, beta) with Gaussian additive noise at the output layer achieved the best IED detection results with a false detection rate of 0.23/min at 90% sensitivity. The EEG classification system obtained a mean EEG classification Leave-One-Institution-Out (LOIO) cross-validation (CV) balanced accuracy (BAC) of 78.1% (area under the curve (AUC) of 0.839) and Leave-One-Subject-Out (LOSO) CV BAC of 79.5% (AUC of 0.856). Since the proposed classification system only takes a few seconds to analyze a 30-min routine EEG, it may help in reducing the human effort required for epilepsy diagnosis.

Accurate prediction of network-level traffic parameters during inclement weather conditions can greatly help in many transportation applications. Rainfall tends to have a quantifiable impact on driving behavior and traffic network performance. This impact is often studied for low-resolution rainfall data on small road networks, whereas this study investigates it in the context of a large traffic network and high-resolution rainfall radar images. First, the impact of rainfall intensity on traffic performance throughout the day and for different road categories is analyzed. Next, it is investigated whether including rainfall information can improve the predictive accuracy of the state-of-the-art traffic forecasting methods. Numerical results show that the impact of rainfall on traffic varies for different rainfall intensities as well as for different times of the day and days of the week. The results also show that incorporating rainfall data into prediction models improves their overall performance. The average reduction in mean absolute percentage error (MAPE) for models with rainfall data is 4.5%. Experiments with downsampled rainfall data were also performed, and it was concluded that incorporating higher resolution weather data does indeed lead to an increase in performance of traffic prediction models.