Search

Relatively recent increased computational power and extensive traffic data availability have provided a unique opportunity to re-investigate drivers’ car-following (CF) behavior. Classic CF models assume drivers’ behavior is only influenced by their preceding vehicle. Recent studies have indicated that considering surrounding vehicles’ information (e.g., multiple preceding vehicles) could affect CF models’ performance. An in-depth investigation of surrounding vehicles’ contribution to CF modeling performance has not been reported in the literature. This study uses a deep-learning model with long short-term memory (LSTM) to investigate to what extent considering surrounding vehicles could improve CF models’ performance. This investigation helps to select the right inputs for traffic flow modeling. Five CF models are compared in this study (i.e., classic, multi-anticipative, adjacent-lanes, following-vehicle, and all-surrounding-vehicles CF models). Performance of the CF models is compared in relation to accuracy, stability, and smoothness of traffic flow. The CF models are trained, validated, and tested by a large publicly available dataset. The average mean square errors (MSEs) for the classic, multi-anticipative, adjacent-lanes, following-vehicle, and all-surrounding-vehicles CF models are 1.58 × 10−3, 1.54 × 10−3, 1.56 × 10−3, 1.61 × 10−3, and 1.73 × 10−3, respectively. However, the results show insignificant performance differences between the classic CF model and multi-anticipative model or adjacent-lanes model in relation to accuracy, stability, or smoothness. The following-vehicle CF model shows similar performance to the multi-anticipative model. The all-surrounding-vehicles CF model has underperformed all the other models.

Electroencephalography (EEG) is an effective non-invasive measurement method to infer user intent in brain-computer interface (BCI) systems for control and communication, however, these systems often lack sufficient accuracy and speed due to low separability of class-conditional EEG feature distributions. Many factors impact system performance, including inadequate training datasets and models’ ignorance of the temporal dependency of brain responses to serial stimuli. Here, we propose a signal model for event-related responses in the EEG evoked with a rapid sequence of stimuli in BCI applications. The model describes the EEG as a superposition of impulse responses time-locked to stimuli corrupted with an autoregressive noise process. The performance of the signal model is assessed in the context of RSVP keyboard, a language-model-assisted EEG-based BCI for typing. EEG data obtained for model calibration from 10 healthy participants are used to fit and compare two models: the proposed sequence-based EEG model and the trial-based feature-class-conditional distribution model that ignores temporal dependencies, which has been used in the previous work. The simulation studies indicate that the earlier model that ignores temporal dependencies may be causing drastic reductions in achievable information transfer rate (ITR). Furthermore, the proposed model, with better regularization, may achieve improved accuracy with fewer calibration data samples, potentially helping to reduce calibration time. Specifically, results show an average 8.6% increase in (cross-validated) calibration AUC for a single channel of EEG, and 54% increase in the ITR in a typing task.

Despite plenty of research being performed in the human movement science, less attention has been paid to the probable method used by the human brain in the higher-level motor planning. The previous studies suggest that the human brain may use a predictive approach to anticipate physical dynamics of the body and the environment to plan a short and collision-free movement trajectory. We propose that the human brain may use a model-based prediction procedure in path planning in which a finite prediction horizon is used to estimate the future state of the body and the environment. A goal-oriented driving task (GDT) in a virtual street was designed to consider the human path planning method in dynamic environments. Two groups of experiments were presented to consider the ability of the human brain in estimation of a dynamic object location and planning a collision-free path. The first group of study includes four GDTs, with different conditions to evaluate how the human planning strategy would change by varying the configuration of the environment. In the second group, the changes of human planning in a visually obscured and blurred situation were considered. The results are in compliance with the theory of using a model-based prediction approach by human brains and indicate that the subjects benefit from a prediction horizon to plan their paths. Our studies provide evidence to introduce possible factors which may be used by the human brain during path planning in dynamic environments.

Lower extremity function recovery is one of the most important goals in stroke rehabilitation. Many paradigms and technologies have been introduced for the lower limb rehabilitation over the past decades, but their outcomes indicate a need to develop a complementary approach. One attempt to accomplish a better functional recovery is to combine bottom-up and top-down approaches by means of brain-computer interfaces (BCIs). In this study, a BCI-controlled robotic mirror therapy system is proposed for lower limb recovery following stroke. An experimental paradigm including four states is introduced to combine robotic training (bottom-up) and mirror therapy (top-down) approaches. A BCI system is presented to classify the electroencephalography (EEG) evidence. In addition, a probabilistic model is presented to assist patients in transition across the experiment states based on their intent. To demonstrate the feasibility of the system, both offline and online analyses are performed for five healthy subjects. The experiment results show a promising performance for the system, with average accuracy of 94% in offline and 75% in online sessions.

The filter-bank based multicarrier FBMC system is a candidate for designing the physical layer of a cognitive radio because of its spectral efficiency and the spectral containment. The main drawback of such a system compared with orthogonal frequency division multiplexing systems is its high computation complexity, because each subcarrier is shaped by a non-rectangular prototype filter. Although poly-phase decomposition is suggested to decrease the sampling rate of filtering, the number of filtering operations multiplications is dramatically increased by the growing number of subcarriers and the amount of the desired spectral containment. Hence, hardware implementation of the FBMC system faces challenges such as high electrical power consumption and large silicon area occupation. In order to reduce computational complexity, a multiplierless filter design based on the canonical signed digit CSD representation is proposed. In this technique, at first, a prototype filter is designed. Then a pre-optimization step is employed to adapt the prototype filter coefficients to system objectives and produce an enriched initial seed for genetic algorithm GA optimization. Finally, a customized GA is employed to jointly optimize and synthesize filter coefficients into the finite precision CSD representation so that the system objectives such as intersymbol-interference, interchannel-interference, and stop-band attenuation remain unchanged against the full-precision representation of coefficients. Copyright © 2014 John Wiley & Sons, Ltd.

A biologically inspired two level method is proposed for real-time path planning in a complex and dynamic environment, employable in ground vehicles. This method takes the advantage of both global and local path finding procedures. In the first level, i.e., global level, the planner utilizes a neural network architecture as a sensory-motor map, similar to the cognitive map used by humans, and an optimization algorithm to produce a coarse path. In the second level, i.e., local level, the global path is improved by employing a model-based prediction method with a finite prediction horizon in a way that future information about the environment is involved in the planner's decision making. In the suggested method, the prediction horizon is variable and is adjusted in each step of the planning in agreement with the kinematic features of the closest obstacle in the visual field of the planner. We considered four different path planning tasks in a virtual dynamic environment to evaluate the performance of the proposed method against the human path planning strategy. The results demonstrate the ability of the method to plan a strategy comparable to the driving scenarios chosen by most subjects and to generate a real-time collision-free path in a dynamic environment with obstacles.

Transcranial current stimulation (tCS) is a non-invasive brain stimulation technique that has shown promise for studying and improving brain function. It can be applied with low-amplitude direct (tDCS), alternating (tACS) or random noise (tRNS) currents. EEG, with its high temporal resolution, portability, and affordability, offers great advantages in investigating the effects of tCS on brain activity. However, concurrent EEG acquisition and tCS stimulation suffers from the drawback that injected current induces significant artifacts on simultaneously acquired EEG. Furthermore, stimulus-current-induced artifacts in measured voltages have powers that are large compared to that of EEG, in the frequency range of interest for EEG analysis. While simple high-pass filtering of the EEG would eliminate artifacts from tDCS, it is not suitable when stimulating with frequencies in the range of significant EEG activity (1–40 Hz). This occurs both in low-frequency tACS/tRNS and in high-pass filtered tRNS, as even in the latter case substantial power will remain at EEG frequencies. In such cases, attenuating tRNS artifacts in EEG requires a more comprehensive model, such as the one we present here.

A new path planning strategy inspired by human path planning is proposed based on the dynamic wave expansion neural network (DWENN) for moving in dynamic environment. The proposed method performs in two phases. In the first phase, a coarse path is produced by using a DWENN and a cognitive map to represent the environment configuration. In the second phase, to improve the coarse path, a predictive approach is iteratively employed by combination of a locally recurrent neural network (LRNN) and a DWENN to plan a motion vector in a finite prediction horizon and executing it in a control horizon. A task is intended to evaluate the performance of the proposed method in crossing a street which includes a moving car as a dynamic obstacle. In this evaluation, different simulations with various prediction and control horizons have been performed. Our results imply that by applying a predictive method and adjusting the prediction and control horizons, DWENN can satisfactorily generate a collision-free path in dynamic environments.

Acute lymphoblastic leukemia (ALL) is the most common subtype of leukemia in children. Although ALL and type 1 diabetes appear to be biologically unrelated, there are common threads in both epidemiology and etiology. Rising incidence rates of both ALL (1) and type 1 diabetes (2) observed over recent decades in many Western countries seem to support common etiological factors (3). In the current study, we report on diabetes-related autoantibodies (Abs) in a group of patients with ALL. Thirty-four consecutive children (19 males and 15 females, mean age 6.2 ± 4.6 years) were referred to our institution in 2004 for newly diagnosed ALL. Patients were tested for Abs to islet and thyroid antigens. After the initial investigation and treatment, 31/34 (91%) patients (3 died in the mean time) were followedup for 6 years to evaluate the evolution of the autoimmune markers and progression toward type 1 diabetes. Glutamic acid decarboxylase (GAD) Abs by direct …