Search Results (12)

Accurate prediction of reinforced concrete shear strength is essential for structural safety, yet datasets often contain a mix of raw geometric and material properties alongside physics-informed engineered features, making optimal feature selection challenging. This study introduces a statistically principled framework that advances feature reduction for neural networks in three novel ways. First, it extends the artificial neural network-based signal-to-noise ratio (ANN-SNR) method, previously limited to classification, into regression tasks for the first time. Second, it couples ANN-SNR with a confidence-interval (CI)-based stopping rule, using the lower bound of the baseline ANN’s R² confidence interval as a rigorous statistical threshold for determining when feature elimination should cease. Third, it systematically evaluates both raw experimental variables and physics-informed engineered features, showing how their combination enhances both robustness and interpretability. Applied to experimental concrete shear strength data, the framework revealed that many low-SNR features in conventional formulations contribute little to predictive performance and can be safely removed. In contrast, hybrid models that combined key raw and engineered features consistently yielded the strongest performance. Overall, the proposed method reduced the input feature set by approximately 45% while maintaining results statistically indistinguishable from baseline and fully optimized models (R² ≈ 0.85). These findings demonstrate that ANN-SNR with CI-based stopping provides a defensible and interpretable pathway for reducing model complexity in reinforced concrete shear strength prediction, offering practical benefits for design efficiency without compromising reliability. Full article

The transition to fully autonomous roadways will include a long period of mixed-autonomy traffic. Mixed-autonomy roadways pose a challenge for autonomous vehicles (AVs) which use conservative driving behaviours to safely negotiate complex scenarios. This can lead to congestion and collisions with human drivers who are accustomed to more confident driving styles. In this work, an explainable multi-variate time series classifier, Time Series Forest (TSF), is compared to two state-of-the-art models in a priority-taking classification task. Responses to left-turning hazards at signalized and stop-sign-controlled intersections were collected using a full-vehicle driving simulator. The dataset was comprised of a combination of AV sensor-collected and V2V (vehicle-to-vehicle) transmitted features. Each scenario forced participants to either take (“go”) or yield (“no go”) priority at the intersection. TSF performed comparably for both the signalized and sign-controlled datasets, although all classifiers performed better on the signalized dataset. The inclusion of V2V data led to a slight increase in accuracy for all models and a substantial increase in the true positive rate of the stop-sign-controlled models. Additionally, incorporating the V2V data resulted in fewer chosen features, thereby decreasing the model complexity while maintaining accuracy. Including the selected features in an AV planning model is hypothesized to reduce the need for conservative AV driving behaviour without increasing the risk of collision. Full article

There is a correlation between cognitive inhibition and compensatory balance response; however, the correlation between response inhibition and gait termination is not clear. Objectives: The purpose of this study was to investigate the gait parameters of the lower extremity that occurred during unplanned gait termination (UGT) in two groups classified by the stop-signal reaction time (SSRT). Methods: Twenty young adults performed a stop-signal task and an unplanned gait termination separately. UGT required subjects to stop on hearing an auditory cue during randomly selected trials. The spatiotemporal and kinematic gait parameters were compared between the groups during UGT. Results: In phase one, the fast group had a significantly greater angle and angular velocity of knee flexion and ankle plantar flexion than the slow group (p < 0.05). Phase two showed that the fast group had a significantly greater angle and angular velocity of knee extension than the slow group (p < 0.05). Concerning the correlation analysis, the angle and angular velocity of knee flexion and ankle plantar flexion showed a negative correlation with the SSRT during UGT in phase one (p < 0.05). Phase two showed that the angle and angular velocity of knee extension was negatively correlated with the SSRT during UGT (p < 0.05). Conclusion: The shorter the SSRT, the greater the angle and joint angular velocity of the ankle or knee joint that were prepared and adjusted for gait termination. The correlation between the SSRT and UGT suggests that a participant’s capacity to inhibit an incipient finger response is associated with their ability to make a corrective gait pattern in a choice-demanding environment. Full article

The aim of this selective review paper is to clarify potential confusion when referring to the term proactive inhibitory control. Illustrated by a concise overview of the literature, we propose defining reactive inhibition as the mechanism underlying stopping an action. On a stop trial, the stop signal initiates the stopping process that races against the ongoing action-related process that is triggered by the go signal. Whichever processes finishes first determines the behavioral outcome of the race. That is, stopping is either successful or unsuccessful in that trial. Conversely, we propose using the term proactive inhibition to explicitly indicate preparatory processes engaged to bias the outcome of the race between stopping and going. More specifically, these proactive processes include either pre-amping the reactive inhibition system (biasing the efficiency of the stopping process) or presetting the action system (biasing the efficiency of the go process). We believe that this distinction helps meaningful comparisons between various outcome measures of proactive inhibitory control that are reported in the literature and extends to experimental research paradigms other than the stop task. Full article

In the Intelligent Transportation System (ITS) realm, queue length estimation is one of an essential yet a challenging task. Queue lengths are important for determining traffic density in traffic lanes so that possible congestion in any lane can be minimized. Smart roadside sensors such as loop detectors, radars and pneumatic road tubes etc. are promising for such tasks though they have a very high installation and maintenance cost. Large scale deployment of surveillance cameras have shown a great potential in the collection of vehicular data in a flexible way and are also cost effective. Similarly, vision-based sensors can be used independently or if required can also augment the functionality of other roadside sensors to effectively process queue length at prescribed traffic lanes. In this research, a CNN-based approach for estimation of vehicle queue length in an urban traffic scenario using low-resolution traffic videos is proposed. The queue length is estimated based on count of total vehicles waiting on a signal. The proposed approach calculates queue length without the knowledge of any onsite camera calibration information. Average vehicle length is approximated to be 5 m. This caters for the vehicles at the far end of the traffic lane that appear smaller in the camera view. Identification of stopped vehicles is done using Deep SORT based object tracking. Due to robust and accurate CNN-based detection and tracking, the queue length estimated by using only the cameras has been very effective. This mostly eliminates the need for fusion with any roadside or in-vehicle sensors. A detailed comparative analysis of vehicle detection models including YOLOv3, YOLOv4, YOLOv5, SSD, ResNet101, and InceptionV3 was performed. Based on this analysis, YOLOv4 was selected as a baseline model for queue length estimation. Using the pre-trained 80-classes YOLOv4 model, an overall accuracy of 73% and 88% was achieved for vehicle count and vehicle count-based queue length estimation, respectively. After fine-tuning of model and narrowing the output classes to vehicle class only, an average accuracy of 83% and 93% was achieved, respectively. This shows the efficiency and robustness of the proposed approach. Full article

The main aim of this study was to investigate the development of selective inhibitory control in middle childhood, a critical period for the maturation of inhibition-related processes. To this end, 64 children aged 6–7 and 56 children aged 10–11 performed a stimulus-selective stop-signal task, which allowed us to estimate not only the efficiency of response inhibition (the stop-signal reaction time or SSRT), but also the strategy adopted by participants to achieve task demands. We found that the adoption of a non-selective (global) strategy characterized by stopping indiscriminately to all stimuli decreased in older children, so that most of them were able to interrupt their ongoing responses selectively at the end of middle childhood. Moreover, compared to younger children, older children were more efficient in their ability to cancel an initiated response (indexed by a shorter SSRT), regardless of which strategy they used. Additionally, we found improvements in other forms of impulsivity, such as the control of premature responding (waiting impulsivity), and attentional-related processes, such as intra-individual variability and distractibility. The present results suggest that middle childhood represents a milestone in the development of crucial aspects of inhibitory control, including selective stopping. Full article

Recent research has clarified the existence of a networked system involving a cortical and subcortical circuitry regulating both cognition and cardiac autonomic control, which is dynamically organized as a function of cognitive demand. The main interactions span multiple temporal and spatial scales and are extensively governed by nonlinear processes. Hence, entropy and (multi)fractality in heart period time series are suitable to capture emergent behavior of the cognitive-autonomic network coordination. This study investigated how entropy and multifractal-multiscale analyses could depict specific cognitive-autonomic architectures reflected in the heart rate dynamics when students performed selective inhibition tasks. The participants ($N=37$) completed cognitive interference (Stroop color and word task), action cancellation (stop-signal) and action restraint (go/no-go) tasks, compared to watching a neutral movie as baseline. Entropy and fractal markers (respectively, the refined composite multiscale entropy and multifractal-multiscale detrended fluctuation analysis) outperformed other time-domain and frequency-domain markers of the heart rate variability in distinguishing cognitive tasks. Crucially, the entropy increased selectively during cognitive interference and the multifractality increased during action cancellation. An interpretative hypothesis is that cognitive interference elicited a greater richness in interactive processes that form the central autonomic network while action cancellation, which is achieved via biasing a sensorimotor network, could lead to a scale-specific heightening of multifractal behavior. Full article

The ability to inhibit or suppress unwanted or inappropriate actions, is an essential component of executive function and cognitive health. The immense selective pressure placed on maintaining inhibitory control processes is exemplified by the relatively small number of instances in which these systems completely fail in the average person’s daily life. Although mistakes and errors do inevitably occur, inhibitory control systems not only ensure that this number is low, but have also adapted behavioral strategies to minimize future failures. The ability of our brains to adapt our behavior and appropriately engage proper motor responses is traditionally depicted as the primary domain of frontal brain areas, despite evidence to the fact that numerous other brain areas contribute. Using the stop-signal task as a common ground for comparison, we review a large body of literature investigating inhibitory control processes across frontal, temporal, and midbrain structures, focusing on our recent work in rodents, in an effort to understand how the brain biases action selection and adapts to the experience of conflict. Full article

Response inhibition has been widely explored using the stop signal paradigm in the laboratory setting. However, the mechanism that demarcates attentional capture from the motor inhibition process is still unclear. Error monitoring is also involved in the stop signal task. Error responses that do not complete, i.e., partial errors, may require different error monitoring mechanisms relative to an overt error. Thus, in this study, we included a “continue go” (Cont_Go) condition to the stop signal task to investigate the inhibitory control process. To establish the finer difference in error processing (partial vs. full unsuccessful stop (USST)), a grip-force device was used in tandem with electroencephalographic (EEG), and the time-frequency characteristics were computed with Hilbert–Huang transform (HHT). Relative to Cont_Go, HHT results reveal (1) an increased beta and low gamma power for successful stop trials, indicating an electrophysiological index of inhibitory control, (2) an enhanced theta and alpha power for full USST trials that may mirror error processing. Additionally, the higher theta and alpha power observed in partial over full USST trials around 100 ms before the response onset, indicating the early detection of error and the corresponding correction process. Together, this study extends our understanding of the finer motor inhibition control and its dynamic electrophysiological mechanisms. Full article

A guidance and information service for a University library based on Wi-Fi signals using fingerprinting as chosen localization method is under development at TU Wien. After a thorough survey of suitable location technologies for the application it was decided to employ mainly Wi-Fi for localization. For that purpose, the availability, performance, and usability of Wi-Fi in selected areas of the library are analyzed in a first step. These tasks include the measurement of Wi-Fi received signal strengths (RSS) of the visible access points (APs) in different areas. The measurements were carried out in different modes, such as static, kinematic and in stop-and-go mode, with six different smartphones. A dependence on the positioning and tracking modes is seen in the tests. Kinematic measurements pose much greater challenges and depend significantly on the duration of a single Wi-Fi scan. For the smartphones, the scan durations differed in the range of 2.4 to 4.1 s resulting in different accuracies for kinematic positioning, as fewer measurements along the trajectories are available for a device with longer scan duration. The investigations indicated also that the achievable localization performance is only on the few meter level due to the small number of APs of the University own Wi-Fi network deployed in the library. A promising solution for performance improvement is the foreseen usage of low-cost Raspberry Pi units serving as Wi-Fi transmitter and receiver. Full article

Mapping with surveying equipment is a time-consuming and cost-intensive procedure that makes the frequent map updating unaffordable. In the last few years, much research has focused on eliminating such problems by counting on crowdsourced data, such as GPS traces. An important source of information in maps, especially under the consideration of forthcoming self-driving vehicles, is the traffic regulators. This information is largely lacking in maps like OpenstreetMap (OSM) and this article is motivated by this fact. The topic of this systematic literature review (SLR) is the detection and recognition of traffic regulators such as traffic lights (signals), stop-, yield-, priority-signs, right of way priority rules and turning restrictions at intersections, by leveraging non imagery crowdsourced data. More particularly, the aim of this study is (1) to identify the range of detected and recognised regulatory types by crowdsensing means, (2) to indicate the different classification techniques that can be used for these two tasks, (3) to assess the performance of different methods, as well as (4) to identify important aspects of the applicability of these methods. The two largest databases of peer-reviewed literature were used to locate relevant research studies and after different screening steps eleven articles were selected for review. Two major findings were concluded—(a) most regulator types can be identified with over 80% accuracy, even using heuristic-driven approaches and (b) under the current progress on the field, no study can be reproduced for comparative purposes nor can solely rely on open data sources due to lack of publicly available datasets and ground truth maps. Future research directions are highlighted as possible extensions of the reviewed studies. Full article

With the popularization and wide application of drones in military and civilian fields, the safety of drones must be considered. At present, the failure and drop rates of drones are still much higher than those of manned aircraft. Therefore, it is imperative to improve the research on the safe landing and recovery of drones. However, most drone navigation methods rely on global positioning system (GPS) signals. When GPS signals are missing, these drones cannot land or recover properly. In fact, with the help of optical equipment and image recognition technology, the position and posture of the drone in three dimensions can be obtained, and the environment where the drone is located can be perceived. This paper proposes and implements a monocular vision-based drone autonomous landing system in emergencies and in unstructured environments. In this system, a novel map representation approach is proposed that combines three-dimensional features and a mid-pass filter to remove noise and construct a grid map with different heights. In addition, a region segmentation is presented to detect the edges of different-height grid areas for the sake of improving the speed and accuracy of the subsequent landing area selection. As a visual landing technology, this paper evaluates the proposed algorithm in two tasks: scene reconstruction integrity and landing location security. In these tasks, firstly, a drone scans the scene and acquires key frames in the monocular visual simultaneous localization and mapping (SLAM) system in order to estimate the pose of the drone and to create a three-dimensional point cloud map. Then, the filtered three-dimensional point cloud map is converted into a grid map. The grid map is further divided into different regions to select the appropriate landing zone. Thus, it can carry out autonomous route planning. Finally, when it stops upon the landing field, it will start the descent mode near the landing area. Experiments in multiple sets of real scenes show that the environmental awareness and the landing area selection have high robustness and real-time performance. Full article