An Adaptive Reference Vector Adjustment Strategy and Improved Angle-Penalized Value Method for RVEA

Decomposition-based evolutionary multiobjective algorithms (MOEAs) divide a multiobjective problem into several subproblems by using a set of predefined uniformly distributed reference vectors and can achieve good overall performance especially in maintaining population diversity. However, they encounter huge difficulties in addressing problems with irregular Pareto fronts (PFs) since many reference vectors do not work during the searching process. To cope with this problem, this paper aims to improve an existing decomposition-based algorithm called reference vector-guided evolutionary algorithm (RVEA) by designing an adaptive reference vector adjustment strategy. By adding the strategy, the predefined reference vectors will be adjusted according to the distribution of promising solutions with good overall performance and the subspaces in which the PF lies may be further divided to contribute more to the searching process. Besides, the selection pressure with respect to convergence performance posed by RVEA is mainly from the length of normalized objective vectors and the metric is poor in evaluating the convergence performance of a solution with the increase of objective size. Motivated by that, an improved angle-penalized distance (APD) method is developed to better distinguish solutions with sound convergence performance in each subspace. To investigate the performance of the proposed algorithm, extensive experiments are conducted to compare it with 5 state-of-the-art decomposition-based algorithms on 3-, 5-, 8-, and 10-objective MaF1–MaF9. The results demonstrate that the proposed algorithm obtains the best overall performance.

Modeling and parameter identification of seated human body with the reference vector guided evolutionary algorithm

The low frequency vibration of the vehicle in motion has a great influence on the ride comfort of occupants. The research on the vibration response characteristics of human body plays a great role in analyzing and improving ride comfort. The purpose of this study was to investigate the parameter identification of seated human body dynamic model. A seven-degree-of-freedom (DOF) lumped parameter model was established to describe the vibration response characteristics of human body. The derivation processes of apparent mass (AM) and seat to head transmissibility (STHT) were performed. After the theoretical calculation of the human body vibration characteristics, we used several different evolutionary algorithms to identify the 23 parameters of the model, including the mass, stiffness and damping parameters. By comparing the results of the five optimization algorithms and comprehensively analyzing the convergence and distribution of the non-dominated solution set, we found that the reference vector guided evolutionary algorithm (RVEA) shows good competitiveness in solving many-objective optimization problem (MaOP), that is, parameter identification of seated human body model in this paper. The AM and STHT calculated by model identification were compared with their measured by experiment. The result shows that the selected seven-DOF model can well describe the vertical vibration characteristics of seated human body and the identification method used in this paper can accurately identify the parameters of lumped parameter model, which provides convenience for the establishment of a complete “road-vehicle-seat-human body” system dynamic model.

A MODEL AND TRAINING METHOD FOR CONTEXT CLASSIFICATION IN CCTV SEWER INSPECTION VIDEO FRAMES

Context. A model and training method for observational context classification in CCTV sewer inspection vide frames was developed and researched. The object of research is the process of detection of temporal-spatial context during CCTV sewer inspections. The subjects of the research are machine learning model and training method for classification analysis of CCTV video sequences under the limited and imbalanced training dataset constraint. Objective. Stated research goal is to develop an efficient context classifier model and training algorithm for CCTV sewer inspection video frames under the constraint of the limited and imbalanced labeled training set. Methods. The four-stage training algorithm of the classifier is proposed. The first stage involves training with soft triplet loss and regularisation component which penalises the network’s binary output code rounding error. The next stage is needed to determine the binary code for each class according to the principles of error-correcting output codes with accounting for intra- and interclass relationship. The resulting reference vector for each class is then used as a sample label for the future training with Joint Binary Cross Entropy Loss. The last machine learning stage is related to decision rule parameter optimization according to the information criteria to determine the boundaries of deviation of binary representation of observations for each class from the corresponding reference vector. A 2D convolutional frame feature extractor combined with the temporal network for inter-frame dependency analysis is considered. Variants with 1D Dilated Regular Convolutional Network, 1D Dilated Causal Convolutional Network, LSTM Network, GRU Network are considered. Model efficiency comparison is made on the basis of micro averaged F1 score calculated on the test dataset. Results. Results obtained on the dataset provided by Ace Pipe Cleaning, Inc confirm the suitability of the model and method for practical use, the resulting accuracy equals 92%. Comparison of the training outcome with the proposed method against the conventional methods indicated a 4% advantage in micro averaged F1 score. Further analysis of the confusion matrix had shown that the most significant increase in accuracy in comparison with the conventional methods is achieved for complex classes which combine both camera orientation and the sewer pipe construction features. Conclusions. The scientific novelty of the work lies in the new models and methods of classification analysis of the temporalspatial context when automating CCTV sewer inspections under imbalanced and limited training dataset conditions. Training results obtained with the proposed method were compared with the results obtained with the conventional method. The proposed method showed 4% advantage in micro averaged F1 score. It had been empirically proven that the use of the regular convolutional temporal network architecture is the most efficient in utilizing inter-frame dependencies. Resulting accuracy is suitable for practical use, as the additional error correction can be made by using the odometer data.

Модель та метод навчання для класифікаційного аналізу рівня води в стічних трубах за даними відео інспекції

Models and training methods for water-level classification analysis on the footage of sewage pipe inspections have been developed and investigated. The object of the research is the process of water-level recognition, considering the spatial and temporal context during the inspection of sewage pipes. The subject of the research is a model and machine learning method for water-level classification analysis on video sequences of pipe inspections under conditions of limited size and an unbalanced set of training data. A four-stage algorithm for training the classifier is proposed. At the first stage of training, training occurs with a softmax triplet loss function and a regularizing component to penalize the rounding error of the network output to a binary code. The next step is to define a binary code (reference vector) for each class according to the principles of error-correcting output codes, but considering the intraclass and interclass relations. The computed reference vector of each class is used as the target label of the sample for further training using the joint cross-entropy loss function. The last stage of machine learning involves optimizing the parameters of the decision rules based on the information criterion to account for the boundaries of deviation of the binary representation of the observations of each class from the corresponding reference vectors. As a classifier model, a combination of 2D convolutional feature extractor for each frame and temporal network to analyze inter-frame dependencies is considered. The different variants of the temporal network are compared. We consider a 1D regular convolutional network with dilated convolutions, 1D causal convolutional network with dilated convolutions, recurrent LSTM-network, recurrent GRU-network. The performance of the models is compared by the micro-averaged metric F1 computed on the test subset. The results obtained on the dataset from Ace Pipe Cleaning (Kansas City, USA) confirm the suitability of the model and training method for practical use, the obtained value of F1-metric is 0.88. The results of training by the proposed method were compared with the results obtained using the traditional method. It was shown that the proposed method provides a 9 % increase in the value of micro-averaged F1-measure.

Many-objective optimization algorithm based on adaptive reference vector

When dealing with multi-objective optimization, the proportion of non-dominated solutions increase rapidly with the increase of optimization objective. Pareto-dominance-based algorithms suffer the low selection pressure towards the true Pareto front. Decomposition-based algorithms may fail to solve the problems with highly irregular Pareto front. Based on the analysis of the two selection mechanism, a dynamic reference-vector-based many-objective evolutionary algorithm(RMaEA) is proposed. Adaptive-adjusted reference vector is used to improve the distribution of the algorithm in global area, and the improved non-dominated relationship is used to improve the convergence in a certain local area. Compared with four state-of-art algorithms on DTLZ benchmark with 5-, 10- and 15-objective, the proposed algorithm obtains 13 minimum mean IGD values and 8 minimum standard deviations among 15 test problem.