In recent years, the m ulti-task learning for k nowledge graph-based r ecommender system, termed MKR, has shown its promising performance and has attracted increasing interest, because a recommendation task and a knowledge graph embedding (KGE) task can help each other to improve the recommendation. However, MKR still has two difficult issues. The first is how fully to capture users' historical behavior pattern in the recommendation task and how fully to utilize deep multi-relation semantic information in the KGE task. The second is how to deal with datasets with different sparsity. Tackling these challenging issues, this paper proposes an enhanced MKR (EMKR) approach with two novelties. First, we propose to utilize the attention mechanism to aggregate users' historical behavior for more accurately mining preferences in the recommendation task, and utilize the relation-aware graph convolutional neural network to fully capture the deep multi-relation neighborhood features in the KGE task, so as to address the first issue. Second, a two-part modeling strategy is proposed for a better representation of users in the recommendation task to expand the expressive ability of the model for adapting to datasets with different sparsity, so as to address the second issue. Extensive experiments are conducted on widely-used datasets and 11 approaches are used for comparison. The results show that the proposed EMKR can achieve substantial gains over the compared state-of-the-art approaches, especially in the situation where user-item interactions are sparse.

Feature selection, which aims to improve the classification accuracy and reduce the size of the selected feature subset, is an important but challenging optimization problem in data mining. Particle swarm optimization (PSO) has shown promising performance in tackling feature selection problems, but still faces challenges in dealing with large-scale feature selection in Big Data environment because of the large search space. Hence, this article proposes a bi-directional feature fixation (BDFF) framework for PSO and provides a novel idea to reduce the search space in large-scale feature selection. BDFF uses two opposite search directions to guide particles to adequately search for feature subsets with different sizes. Based on the two different search directions, BDFF can fix the selection states of some features and then focus on the others when updating particles, thus narrowing the large search space. Besides, a self-adaptive strategy is designed to help the swarm concentrate on a more promising direction for search in different stages of evolution and achieve a balance between exploration and exploitation. Experimental results on 12 widely-used public datasets show that BDFF can improve the performance of PSO on large-scale feature selection and obtain smaller feature subsets with higher classification accuracy.

Three-dimensional (3D) ground-penetrating radar is an effective method for detecting internal crack damage in pavement structures. Inefficient manual interpretation of radar images and high personnel requirements have substantially restrained the generalization of 3D ground-penetrating radar. An improved Crack Unet model based on the Unet semantic segmentation model is proposed herein for 3D ground-penetrating radar crack image processing. The experiment showed that the MPA, MioU, and accuracy of the model were improved, and it displayed better capacity in the radar image crack segmentation task than current mainstream algorithms do, such as deepLabv3, PSPNet, and Unet. In the test dataset without cracks, Crack Unet is on the same level as deepLabv3 and PSPNet, which can meet engineering requirements and display a significant improvement compared with Unet. According to the ablation experiment, the MPA and MioU of Unet configured with PMDA, MC-FS, and RS modules were larger than those of Unet configured with one or two modules. The PMDA module adopted by the Crack Unet model showed a higher MPA and MioU than the SE module and the CBAM module did, respectively. The results show that the Crack Unet model has a better segmentation ability than the current mainstream algorithms do in the task of the crack segmentation of radar images, and the performance of crack segmentation is significantly improved compared with the Unet model. The Crack Unet model has excellent engineering application value in the task of the crack segmentation of radar images.

Particle swarm optimization (PSO) is a promising method for feature selection. When using PSO to solve the feature selection problem, the probability of each feature being selected and not being selected is the same in the beginning and is optimized during the evolutionary process. That is, the feature selection probability is optimized from symmetry (i.e., 50% vs. 50%) to asymmetry (i.e., some are selected with a higher probability, and some with a lower probability) to help particles obtain the optimal feature subset. However, when dealing with large-scale features, PSO still faces the challenges of a poor search performance and a long running time. In addition, a suitable representation for particles to deal with the discrete binary optimization problem of feature selection is still in great need. This paper proposes a compressed-encoding PSO with fuzzy learning (CEPSO-FL) for the large-scale feature selection problem. It uses the N-base encoding method for the representation of particles and designs a particle update mechanism based on the Hamming distance and a fuzzy learning strategy, which can be performed in the discrete space. It also proposes a local search strategy to dynamically skip some dimensions when updating particles, thus reducing the search space and reducing the running time. The experimental results show that CEPSO-FL performs well for large-scale feature selection problems. The solutions obtained by CEPSO-FL contain small feature subsets and have an excellent performance in classification problems.

Nowadays, recommendation systems (RSs) have been widely used in many real-world applications. However, traditional recommendation techniques mainly aim at improving recommendation accuracy, while other metrics to measure the performance of the RSs are not considered. In this paper, a multiobjective recommendation model that considers different metrics, including accuracy, diversity, and novelty of recommendations is established. Compared with recommendation models that only consider accuracy, this model can recommend more different items with higher diversity and more fresh items with higher novelty to enhance the long-term performance of RSs. Moreover, to efficiently solve this multiobjective recommendation model, a multi-population genetic algorithm (MPGA), which follows the multiple populations for multiple objectives (MPMO) framework, is proposed. As far as we know, it is the first time that the advanced MPMO framework is used in RSs. We conduct comparison experiments on three real-world datasets with three state-of-the-art multiobjective recommendation algorithms and two traditional multiobjective evolutionary algorithms. The experimental results indicate that the performance of MPGA is better than all the compared methods.