Computer-vision and deep-learning techniques are being increasingly applied to inspect, monitor, and assess infrastructure conditions including detection of cracks. Traditional vision-based methods to detect cracks lack accuracy and generalization to work on complicated infrastructural conditions. This paper presents a novel context-aware deep convolutional semantic segmentation network to effectively detect cracks in structural infrastructure under various conditions. The proposed method applies a pixel-wise deep semantic segmentation network to segment the cracks on images with arbitrary sizes without retraining the prediction network. Meanwhile, a context-aware fusion algorithm that leverages local cross-state and cross-space constraints is proposed to fuse the predictions of image patches. This method is evaluated on three datasets: CrackForest Dataset (CFD) and Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) and a Customized Field Test Dataset (CFTD) and achieves Boundary F1 (BF) score of 0.8234, 0.8252, and 0.7937 under 2-pixel error tolerance margin in CFD, TRIMMD, and CFTD, respectively. The proposed method advances the state-of-the-art performance of BF score by approximately 2.71% in CFD, 1.47% in TRIMMD, and 4.14% in CFTD. Moreover, the averaged processing time of the proposed system is 0.7 s on a typical desktop with Intel^® Quad-Core™ i7-7700 CPU@3.6 GHz Processor, 16GB RAM and NVIDIA GeForce GTX 1060 6GB GPU for an image of size 256 × 256 pixels.

Probabilistic neural networks (PNNs) are artificial neural network algorithms widely used in pattern recognition and classification problems. In the traditional PNN algorithm, the probability density function (PDF) is approximated using the entire training dataset for each class. In some complex datasets, classmate clusters may be located far from each other and these distances between clusters may cause a reduction in the correct class's posterior probability and lead to misclassification. This paper presents a novel PNN algorithm, the competitive probabilistic neural network (CPNN). In the CPNN, a competitive layer ranks kernels for each class and an optimum fraction of kernels are selected to estimate the class-conditional probability. Using a stratified, repeated, random subsampling cross-validation procedure and 9 benchmark classification datasets, CPNN is compared to both traditional PNN and the state of the art(e.g. enhanced probabilistic neural network, EPNN). These datasets are examined with and without noise and the algorithm is evaluated with several ratios of training to testing data. In all datasets (225 simulation categories), performance percentages of both CPNN and EPNN are greater than or equivalent to that of the traditional PNN; in 73% of simulation categories, the CPNN analyses show modest improvement in performance over the state of the art.

Researchers in the structural health monitoring field have recently focused on using instrumented vehicles, usually equipped with accelerometers, as mobile bridge inspection instruments. The vehicle plays two roles: that of the measurement device and that of the excitation source. Permanent changes to the bridge’s stiffness due to damage or wear may manifest as changes in the bridge’s fundamental frequencies. In vehicle-based inspection, bridge frequencies are extracted from vehicle responses. These bridge frequencies may be estimated periodically as a continuing bridge condition assessment. This paper establishes closed-form solutions for bridge and vehicle vibration as a vehicle traverses a two-span continuous bridge and provides a method of bridge frequency extraction from vehicle response. Results are validated using finite-element simulations and compared against the literature. Results show that bridge frequencies observed by the vehicle manifest as two peaks shifted below and above the fundamental bridge frequency. These shifts are linear functions and the average of these shifted bridge frequencies approximates the fundamental bridge frequency to within 7% error; this error decreases to 2% for equal spans.

In Late Pleistocene North America colonizing hunter-gatherers knapped and used Clovis fluted projectile points. During their expansion the size and shape of Clovis points changed significantly. Archaeologists know that cultural drift contributed to this variation, but is it possible that this single source could alone generate so much variation so quickly? We present the first of several experimental studies exploring whether Clovis size and shape variation results in performance differences, focusing here on how deeply different Clovis point forms penetrate a target. Our ballistics experiment demonstrates that seven different Clovis point forms penetrated the same target with different effectiveness. Even after tip cross-sectional perimeter is accounted for, there are significant differences in penetration depths between two of the point types. These results are consistent with the hypothesis that Clovis people in different times and places may have chosen specific attributes to provide them with a selective functional advantage.