Search results

This paper aims to develop an effective framework which combines Bayesian optimized convolutional neural networks (BOCNN) with Monte Carlo simulation for slope reliability analysis.

The Bayesian optimization technique is firstly used to find the optimal structure of CNN based on the empirical CNN model established in a trial and error manner. The proposed methodology is illustrated through a two-layered soil slope and a cohesive slope with spatially variable soils at different scales of fluctuation.

The size of training data suite, T, has a significant influence on the performance of trained CNN. In general, a trained CNN with larger T tends to have higher coefficient of determination (R²) and smaller root mean square error (RMSE). The artificial neural networks (ANN) and response surface method (RSM) can provide comparable results to CNN models for the slope reliability where only two random variables are involved whereas a significant discrepancy between the slope failure probability (P_f) by RSM and that predicted by CNN has been observed for slope with spatially variable soils. The RSM cannot fully capture the complicated relationship between the factor of safety (FS) and spatially variable soils in an effective and efficient manner. The trained CNN at a smaller the scale of fluctuation (λ) exhibits a fairly good performance in predicting the P_f for spatially variable soils at higher λ with a maximum percentage error not more than 10%. The BOCNN has a larger R² and a smaller RMSE than empirical CNN and it can provide results fairly equivalent to a direct Monte Carlo Simulation and therefore serves a promising tool for slope reliability analysis within spatially variable soils.

A geotechnical engineer could use the proposed method to perform slope reliability analysis.

Slope reliability can be efficiently and accurately analyzed by the proposed framework.

During service period, due to the overload or other non-load factors, diagonal cracks of the pre-stressed concrete beam are seriously affecting the safety of the bridge structure. The purpose of this paper is to quickly realize the shear bearing capacity and shear stiffness through maximum width of the diagonal cracks and make correct judgments.

Through the shear failure test of four test beams, collecting data of diagonal cracks and shear stiffness loss value. According to the deformation curve of the shear stiffness, and combined with the calculation formula of the maximum width of diagonal cracks, the formula for calculating the effective shear stiffness based on the maximum width of diagonal cracks is deduced, then the results are verified by test data. Data regression method is used to establish the effective shear stiffness loss ratio calculation formula, the maximum width of diagonal cracks used as a variable factor, and the accuracy of this formula is verified by comparing the shear failure test results of pre-stressed hollow plates.

With the increase in width of the diagonal crack, the loss rate of shear stiffness of the concrete beams is initially fast and then becomes slow. The calculation formulae for shear stiffness based on the maximum width of the diagonal cracks were deduced, and the feasibility and accuracy of the formulae were verified by analysis and calculation of shear test data.

A method for quickly determine the shear stiffness loss of structures by using maximum width of the diagonal cracks is established, and using this method, engineers can quickly determine effective shear stiffness loss ratio, without complex calculations. So this method not only ensures the safety of human life, but also saves money.

Object detection models have gained considerable popularity as they aid in lot of applications, like monitoring, video surveillance, etc. Object detection through the video tracking faces lot of challenges, as most of the videos obtained as the real time stream are affected due to the environmental factors.

This research develops a system for crowd tracking and crowd behaviour recognition using hybrid tracking model. The input for the proposed crowd tracking system is high density crowd videos containing hundreds of people. The first step is to detect human through visual recognition algorithms. Here, a priori knowledge of location point is given as input to visual recognition algorithm. The visual recognition algorithm identifies the human through the constraints defined within Minimum Bounding Rectangle (MBR). Then, the spatial tracking model based tracks the path of the human object movement in the video frame, and the tracking is carried out by extraction of color histogram and texture features. Also, the temporal tracking model is applied based on NARX neural network model, which is effectively utilized to detect the location of moving objects. Once the path of the person is tracked, the behaviour of every human object is identified using the Optimal Support Vector Machine which is newly developed by combing SVM and optimization algorithm, namely MBSO. The proposed MBSO algorithm is developed through the integration of the existing techniques, like BSA and MBO.

The dataset for the object tracking is utilized from Tracking in high crowd density dataset. The proposed OSVM classifier has attained improved performance with the values of 0.95 for accuracy.

This paper presents a hybrid high density video tracking model, and the behaviour recognition model. The proposed hybrid tracking model tracks the path of the object in the video through the temporal tracking and spatial tracking. The features train the proposed OSVM classifier based on the weights selected by the proposed MBSO algorithm. The proposed MBSO algorithm can be regarded as the modified version of the BSO algorithm.

Classifying moving objects in video sequences has been extensively studied, yet it is still an ongoing problem. In this paper, we propose to solve moving objects classification problem via an extended version of two-dimensional principal component analysis (2DPCA), named as category-wise 2DPCA (CW2DPCA). A key component of the CW2DPCA is to independently construct optimal projection matrices from object-specific training datasets and produce category-wise feature spaces, wherein each feature space uniquely captures the invariant characteristics of the underlying intra-category samples. Consequently, on one hand, CW2DPCA enables early separation among the different object categories and, on the other hand, extracts effective discriminative features for representing both training datasets and test objects samples in the classification model, which is a nearest neighbor classifier. For ease of exposition, we consider human/vehicle classification, although the proposed CW2DPCA-based classification framework can be easily generalized to handle multiple objects classification. The experimental results prove the effectiveness of CW2DPCA features in discriminating between humans and vehicles in two publicly available video datasets.