Journal of Intelligent & Fuzzy Systems - Volume 42, issue 3

Authors: Huang, Yuchong | Xu, Ning | Wang, Nan | Li, Jie

Article Type: Research Article

Abstract: Through innovatively introducing the receding horizon into probabilistic model checking, an online strategy synthesis method for multi-robot systems from local automatons is proposed to complete complex tasks that are assigned to each robot. Firstly, each robot is modeled as a Markov decision process which models both probabilistic and nondeterministic behavior. Secondly, the task specification of each robot is expressed as a linear temporal logic formula. For some tasks that robots cannot complete by themselves, the collaboration requirements take the form of atomic proposition into the LTL specifications. And the LTL specifications are transformed to deterministic rabin automatons over which a …task progression metric is defined to determine the local goal states in the finite-horizon product systems. Thirdly, two horizons are set to determine the running steps in automatons and MDPs. By dynamically building local finite-horizon product systems, the collaboration strategies are synthesized iteratively for each robot to satisfy the task specifications with maximum probability. Finally, through simulation experiments in an indoor environment, the results show that the method can synthesize correct strategies online for multi-robot systems which has no restriction on the LTL operators and reduce the computational burden brought by the automaton-based approach. Show more

Keywords: Receding horizon, linear temporal logic, Markov decision process, probabilistic model checking, multi-robot collaboration

DOI: 10.3233/JIFS-211427

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2057-2069, 2022

Authors: She, Chunyan | Zeng, Shaohua

Article Type: Research Article

Abstract: Outlier detection is a hot issue in data mining, which has plenty of real-world applications. LOF (Local Outlier Factor) can capture the abnormal degree of objects in the dataset with different density levels, and many extended algorithms have been proposed in recent years. However, the LOF needs to search the nearest neighborhood of each object on the whole dataset, which greatly increases the time cost. Most of these extended algorithms only consider the distance between an object and its neighborhood, but ignore the local distribution of an object within its neighborhood, resulting in a high false-positive rate. To improve the …running speed, a rough clustering based on triple fusion is proposed, which divides a dataset into several subsets and outlier detection is performed only on each subset. Then, considering the local distribution of an object within its neighborhood, a new local outlier factor is constructed to estimate the abnormal degree of each object. Finally, the experimental results indicate that the proposed algorithm has better performance and lower running time than the others. Show more

Keywords: Outlier detection, local outlier factor, rough Clustering

DOI: 10.3233/JIFS-211433

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2071-2082, 2022

Authors: Wang, Yun | Jin, Xin | Yang, Jie | Jiang, Qian | Tang, Yue | Wang, Puming | Lee, Shin-Jye

Article Type: Research Article

Abstract: Multi-focus image fusion is a technique that integrates the focused areas in a pair or set of source images with the same scene into a fully focused image. Inspired by transfer learning, this paper proposes a novel color multi-focus image fusion method based on deep learning. First, color multi-focus source images are fed into VGG-19 network, and the parameters of convolutional layer of the VGG-19 network are then migrated to a neural network containing multilayer convolutional layers and multilayer skip-connection structures for feature extraction. Second, the initial decision maps are generated using the reconstructed feature maps of a deconvolution module. …Third, the initial decision maps are refined and processed to obtain the second decision maps, and then the source images are fused to obtain the initial fused images based on the second decision maps. Finally, the final fused image is produced by comparing the Q ABF metrics of the initial fused images. The experimental results show that the proposed method can effectively improve the segmentation performance of the focused and unfocused areas in the source images, and the generated fused images are superior in both subjective and objective metrics compared with most contrast methods. Show more

Keywords: Deep learning, feature extraction, multi-focus images fusion, neural networks, transfer learning

DOI: 10.3233/JIFS-211434

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2083-2102, 2022

Authors: Özdemir, Özgür | Akın, Emre Salih | Velioğlu, Rıza | Dalyan, Tuğba

Article Type: Research Article

Abstract: Machine translation (MT) is an important challenge in the fields of Computational Linguistics. In this study, we conducted neural machine translation (NMT) experiments on two different architectures. First, Sequence to Sequence (Seq2Seq) architecture along with a variation that utilizes attention mechanism is performed on translation task. Second, an architecture that is fully based on the self-attention mechanism, namely Transformer, is employed to perform a comprehensive comparison. Besides, the contribution of employing Byte Pair Encoding (BPE) and Gumbel Softmax distributions are examined for both architectures. The experiments are conducted on two different datasets: TED Talks that is one of the popular …benchmark datasets for NMT especially among morphologically rich languages like Turkish and WMT18 News dataset that is provided by The Third Conference on Machine Translation (WMT) for shared tasks on various aspects of machine translation. The evaluation of Turkish-to-English translations’ results demonstrate that the Transformer model with combination of BPE and Gumbel Softmax achieved 22.4 BLEU score on TED Talks and 38.7 BLUE score on WMT18 News dataset. The empirical results support that using Gumbel Softmax distribution improves the quality of translations for both architectures. Show more

Keywords: Neural machine translation, Gumbel Softmax, sequence to sequence, transformer

DOI: 10.3233/JIFS-211453

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2103-2113, 2022

Authors: Tian, Yun Bo | Ma, Zhen Ming

Article Type: Research Article

Abstract: Both Heronian mean (HM) operators and Bonferroni mean (BM) operators can capture the interrelationship between input arguments and have been a hot research topic as a useful aggregation technique in fuzzy and intuitionistic fuzzy environments. In this paper, associated with the common characters of these operators we propose the covering-based compound mean operators in fuzzy environments to capture various interrelationships between input arguments, some desirable properties and special cases of the proposed mean operators are provided. Then, conditions under which these covering-based compound mean operators can be directly used to aggregate the membership degrees and nonmembership degrees of intuitionistic fuzzy …information, are provided. In particular, novel intuitionistic fuzzy HM operators and intuitionistic fuzzy BM operators are directly derived from the classical ones. We list the detailed steps of multiple attribute decision making with the developed aggregation operators, and give a comparison of the new extensions of BM operators by this paper with the corresponding existing ones to prove the rationality and effectiveness of the proposed method. Show more

Keywords: Heronian mean operator, Bonferroni mean operator, Covering-based compound mean operator, Intuitionistic fuzzy sets, Multiple attribute decision making

DOI: 10.3233/JIFS-211457

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2115-2126, 2022

Authors: He, Fang | Zhang, Wenyu | Yan, Zhijia

Article Type: Research Article

Abstract: Credit scoring has become increasingly important for financial institutions. With the advancement of artificial intelligence, machine learning methods, especially ensemble learning methods, have become increasingly popular for credit scoring. However, the problems of imbalanced data distribution and underutilized feature information have not been well addressed sufficiently. To make the credit scoring model more adaptable to imbalanced datasets, the original model-based synthetic sampling method is extended herein to balance the datasets by generating appropriate minority samples to alleviate class overlap. To enable the credit scoring model to extract inherent correlations from features, a new bagging-based feature transformation method is proposed, which …transforms features using a tree-based algorithm and selects features using the chi-square statistic. Furthermore, a two-layer ensemble method that combines the advantages of dynamic ensemble selection and stacking is proposed to improve the classification performance of the proposed multi-stage ensemble model. Finally, four standardized datasets are used to evaluate the performance of the proposed ensemble model using six evaluation metrics. The experimental results confirm that the proposed ensemble model is effective in improving classification performance and is superior to other benchmark models. Show more

Keywords: Ensemble learning, credit scoring, synthetic sampling, feature transformation

DOI: 10.3233/JIFS-211467

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2127-2142, 2022

Authors: Shao, Dangguo | Li, Chengyao | Huang, Chusheng | An, Qing | Xiang, Yan | Guo, Junjun | He, Jianfeng

Article Type: Research Article

Abstract: Aiming at the low effectiveness of short texts feature extraction, this paper proposes a short texts classification model based on the improved Wasserstein-Latent Dirichlet Allocation (W-LDA), which is a neural network topic model based on the Wasserstein Auto-Encoder (WAE) framework. The improvements of W-LDA are as follows: Firstly, the Bag of Words (BOW) input in the W-LDA is preprocessed by Term Frequency–Inverse Document Frequency (TF-IDF); Subsequently, the prior distribution of potential topics in W-LDA is replaced from the Dirichlet distribution to the Gaussian mixture distribution, which is based on the Variational Bayesian inference; And then the sparsemax function layer is …introduced after the hidden layer inferred by the encoder network to generate a sparse document-topic distribution with better topic relevance, the improved W-LDA is named the Sparse Wasserstein-Variational Bayesian Gaussian mixture model (SW-VBGMM); Finally, the document-topic distribution generated by SW-VBGMM is input to BiGRU (Bidirectional Gating Recurrent Unit) for the deep feature extraction and the short texts classification. Experiments on three Chinese short texts datasets and one English dataset represent that our model is better than some common topic models and neural network models in the four evaluation indexes (accuracy, precision, recall, F1 value) of text classification. Show more

Keywords: Short texts classification, neural network topic model, Variational Bayesian Gaussian mixture model (VBGMM), sparsemax, BiGRU (Bidirectional Gating Recurrent Unit)

DOI: 10.3233/JIFS-211471

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2143-2155, 2022

Authors: Yang, Yaxu | Guo, Zixue | He, Zefang

Article Type: Research Article

Abstract: The occurrence of public health emergency will cause huge economic losses and casualties, which posed a huge threat to the economic and social development. In response to the emergency, a large amount of emergency relief supplies will be transported to the affected areas. Faced with this public health emergency of international concern, the concept of emergency logistics capacity and the evaluation model based on probabilistic linguistic term sets are proposed. In this paper, the emergency logistics capability evaluation is transformed into user demand evaluation, and the importance of each index of emergency logistics capability is determined by using Quality Function …Deployment (QFD) and prospect theory. Under the probabilistic language information environment, a multi-attribute decision making method is established by using TODIM method. Finally, an example is given to verify the feasibility of the proposed method. Show more

Keywords: Emergency logistics capacity, probabilistic linguistic term sets, quality function deployment (QFD)

DOI: 10.3233/JIFS-211495

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2157-2168, 2022

Authors: Zheng, Wei | Du, Qing | Fan, Yongjian | Tan, Lijuan | Xia, Chuanlin | Yang, Fengyu

Article Type: Research Article

Abstract: Personalized exercise recommendation is an important research project in the field of online learning, which can explore students’ strengths and weaknesses and tailor exercises for them. However, programming exercises differs from other disciplines or types of exercises due to the comprehensive of the exercises and the specificity of program debugging. In order to assist students in learning programming, this paper proposes a programming exercise recommendation algorithm based on knowledge structure tree (KSTER). Firstly, the algorithm provides a calculation method for quantifying students’ cognitive level to obtain their knowledge needs through individual learning-related data. Secondly, a knowledge structure tree is constructed …based on the association relationship of knowledge points, and a learning objective prediction method is proposed by combining the knowledge needs and the knowledge structure tree to represent and update the learning objective. Finally, KSTER imports a matching operator that calculates cognitive level and exercise difficulty based on learning objectives, and makes top-η recommendation for exercises. Experiments show that the proposed algorithm significantly outperforms the other algorithms in both precision and recall. The comparison experiments with real-world data demonstrate that KSTER effectively improves students’ learning efficiency. Show more

Keywords: Personalized recommendation, learning objectives, knowledge structure tree, online learning

DOI: 10.3233/JIFS-211499

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2169-2180, 2022

Authors: Dai, Tianhong | Cong, Shijie | Huang, Jianping | Zhang, Yanwen | Huang, Xinwang | Xie, Qiancheng | Sun, Chunxue | Li, Kexin

Article Type: Research Article

Abstract: In agricultural production, weed removal is an important part of crop cultivation, but inevitably, other plants compete with crops for nutrients. Only by identifying and removing weeds can the quality of the harvest be guaranteed. Therefore, the distinction between weeds and crops is particularly important. Recently, deep learning technology has also been applied to the field of botany, and achieved good results. Convolutional neural networks are widely used in deep learning because of their excellent classification effects. The purpose of this article is to find a new method of plant seedling classification. This method includes two stages: image segmentation and …image classification. The first stage is to use the improved U-Net to segment the dataset, and the second stage is to use six classification networks to classify the seedlings of the segmented dataset. The dataset used for the experiment contained 12 different types of plants, namely, 3 crops and 9 weeds. The model was evaluated by the multi-class statistical analysis of accuracy, recall, precision, and F1-score. The results show that the two-stage classification method combining the improved U-Net segmentation network and the classification network was more conducive to the classification of plant seedlings, and the classification accuracy reaches 97.7%. Show more

Keywords: Deep learning, plant seedlings classification, machine learning, U-Net

DOI: 10.3233/JIFS-211507

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2181-2191, 2022