Unsupervised anomaly detection methods are at the forefront of industrial anomaly detection efforts and have made notable progress. Previous work primarily used 2D information as input, while multi-modal industrial an...
详细信息
This paper presents an effective method that can detect fabric defects. The method utilizes the optimal Gabor filter and binary random drift particle swarm algorithm (BRDPSO) that can implement feature selection and p...
详细信息
Fine-Grained Visual Classification (FGVC) is a challenging task due to subtle differences among subordinate categories. Many current FGVC approaches focus on identifying and locating discriminative regions, but neglec...
详细信息
Nowadays, deep-learning based NLP models are usually trained with large-scale third-party data which can be easily injected with malicious backdoors. Thus, BackDoor Attack (BDA) study has become a trending research to...
详细信息
The existing social network matching algorithms have problems in processing text attribute information, as they cannot handle polysemy issues of word meanings well and cannot effectively extract deep semantic informat...
详细信息
Heuristic algorithms have been developed to find approximate solutions for high-utility itemset mining (HUIM) problems that compensate for the performance bottlenecks of exact algorithms. However, heuristic algorithms...
详细信息
In the community of artificial intelligence, significant progress has been made in encoding sequential data using deep learning techniques. Nevertheless, how to effectively mine useful information from channel dimensi...
High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data ***,most HUIM algorithms are mainly developed on a single machine,which is ine...
详细信息
High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data ***,most HUIM algorithms are mainly developed on a single machine,which is inefficient for big data since limited memory and processing capacities are available.A parallel efficient high-utility itemset mining(P-EFIM)algorithm is proposed based on the Hadoop platform to solve this problem in this *** P-EFIM,the transaction-weighted utilization values are calculated and ordered for the itemsets with the MapReduce *** the ordered itemsets are renumbered,and the low-utility itemsets are pruned to improve the dataset *** the Map phase,the P-EFIM algorithm divides the task into multiple independent *** uses the proposed S-style distribution strategy to distribute the subtasks evenly across all nodes to ensure ***,the P-EFIM uses the EFIM algorithm to mine each subtask dataset to enhance the performance in the Reduce *** are performed on eight datasets,and the results show that the runtime performance of P-EFIM is significantly higher than that of the PHUI-Growth,which is also HUIM algorithm based on the Hadoop framework.
In evolutionary many-objective optimization, achieving better balance between convergence and diversity of the population is a crucial way to improve the efficiency of the algorithm. However, diversity measure may sel...
详细信息
In evolutionary many-objective optimization, achieving better balance between convergence and diversity of the population is a crucial way to improve the efficiency of the algorithm. However, diversity measure may select the individuals having good diversity but degrade the convergence process to a certain extent. If the convergence measure focuses on the convergence of the individuals too much, it may lead to local convergence. The selection pressure achieves a severe loss, especially when the Pareto dominance selection mechanism is difficult to select solutions. To address these issues, a many-objective evolutionary algorithm based on new angle penalized distance is proposed in this paper, which is termed MaOEA-NAPD. In MaOEA-NAPD, it could dynamically balance the convergence and diversity of the population concerning their importance degree during the evolutionary process based on new angle penalized distance. In order to enhance the selection probability of better solutions in the mating pool, new convergence measure and diversity measure are introduced according to the achievement scalarizing function and angle based crowding degree estimation, respectively. The performance of the proposed method is evaluated and compared with five state-of-the-art algorithms on the WFG test suites with up to 15 objectives. Experimental results show the superior performance of MaOEA-NAPD than the compared algorithms on all the considered test instances.
As many superior convolutional neural networks (CNNs) have been proposed in recent years, CNNs have played an important role in computer vision. However, manually-designing CNN architecture is difficult since expertis...
详细信息
As many superior convolutional neural networks (CNNs) have been proposed in recent years, CNNs have played an important role in computer vision. However, manually-designing CNN architecture is difficult since expertise is required. Therefore, several automatic search algorithms have been proposed for neural architecture search, which usually have considerable computational complexity and the search space is limited. To address these problems, an efficient and flexible CNN architecture search algorithm (EF-CNN) is proposed in this paper. In EF-CNN, a flexible architecture search space is constructed by considering the depth, width, and lightweight blocks. In order to improve the reliability of the architecture while reducing the computational time, a multi-objective fitness correction method is proposed in EF-CNN based on the divided datasets, where the accuracy and computational complexity of architecture are considered simultaneously to design CNN. The experimental results on CIFAR-10 and CIFAR-100 indicate that the performance of CNN architecture designed by EF-CNN is very competitive while the computational time is greatly reduced.
暂无评论