Journal of Intelligent & Fuzzy Systems - Volume 45, issue 5

Authors: Antony Vigil, M.S. | Agarwal, Amit | Brahma Rao, K.B.V. | Meena Devi, G. | Farooq, Mohd Umar | Ganeshan, P. | Alyami, Nouf M. | Almeer, Rafa | Raghavan, S.S.

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-234188

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7191-7203, 2023

Authors: Fan, Jianping | Wang, Min | Wu, Meiqin

Article Type: Research Article

Abstract: Linguistic Pythagorean fuzzy set (LPFS) combines Pythagorean fuzzy sets and linguistic term sets, which can effectively deal with fuzzy information in multi-criteria decision-making (MCDM). The entropy weight method (EWM) can reflect the objectivity of decision information, while the best-worst method (BWM) can reflect the subjectivity of decision-makers. The interactive multi-criteria decision-making (TODIM) method can describe the different preferences of decision-makers for gains and losses. In this paper, EWM, BWM, and TODIM are combined and applied to LPFS for the first time. First, we calculate the objective weight and subjective weight of each criterion through EWM and BWM and combine them …to get the final weight to balance subjectivity and objectivity. Then, this paper selects the best scheme through TODIM sorting. In conclusion, the LPFS-EWM-BWM-TODIM model is established in this paper. Finally, the paper applies this model to the selection of corporate investment strategy and green mine, verifies the effectiveness of the method, and carries out comparative analysis and sensitivity analysis, proving the rationality and robustness of the model. Show more

Keywords: Linguistic Pythagorean fuzzy set (LPFS), EWM, BWM, TODIM

DOI: 10.3233/JIFS-224294

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7205-7220, 2023

Authors: Pan, Yiming | Cheng, Hua | Fang, Yiquan | Liu, Yufei

Article Type: Research Article

Abstract:  Pre-trained Visual Language Models (VLMs) like CLIP have shown great potential in the multimodal domain. Among this, using different modal contexts and interaction features to construct prompt can stimulate the model’s prior knowledge circuit more accurately, thus generating better outputs. However, in CLIP, the formal mismatch of textual descriptions between the pre-training and inference phases results in a suboptimal representation ability of prompt, which is detrimental to model alignment learning. Therefore, R egion-A ttention P rompt (RAP) is proposed, which introduces region features to enrich the semantic representation of prompt. RAP is acquired by the Cross-Attention mechanism between images and …texts, and it is essentially a region-level prompt with category-sensitive properties. For each category, RAP adaptively assigns greater attention weight to image regions that are more semantically relevant to the category. Besides, CLIP is equipped with RAP (called RA-CLIP) to improve image classification performance in generalization scenarios. Extensive experiments demonstrate that RA-CLIP outperforms the current SOTA CoCoOp 0.4% - 4.16% on base classes and 0.25% - 11.34% on new classes, across 7 datasets. In addition, we show that focusing on category-related regions to construct prompt can further improve the model’s alignment ability. Show more

Keywords: Prompt learning, CLIP, Cross-Attention mechanism, image classfication

DOI: 10.3233/JIFS-230879

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7221-7235, 2023

Authors: Xiao, Yanjun | Zhao, Yue | Han, Furong | Peng, Kai | Wan, Feng

Article Type: Research Article

Abstract: The mechanical structures of the rapier loom are strongly coupled, resulting in faults that are characterized by strong coupling, hierarchy, phase dynamics, and a transient nature. However, current fault diagnosis methods using a single approach are not satisfactory. Additionally, fault diagnosis of the entire operation cycle of the rapier loom equipment is lacking. This paper proposes a fault tree diagnosis method with probabilistic neural network optimization to build a complete fault diagnosis system for rapier looms and improve their intelligent diagnosis capability. The method has strong fault tolerance and self-adaptive capability, allowing for accurate location of the root cause of …the fault from multiple fault sources. By accumulating fault samples and continuously improving the diagnosis network, the accuracy of diagnosis can be further enhanced. Initially, the failure mechanism of key subsystems of rapier loom is analyzed. A fault tree model is established for each subsystem based on expert experience and historical data. The model identifies the characteristic sign quantities of typical fault types and serves as the basic input for fault identification. A probabilistic neural network is used to train the fault sample set and complete the diagnosis of the cause of the fault. According to field experiments, the proposed method has demonstrated a significant improvement in the efficiency of locating and identifying fault signs in rapier looms. This improvement allows for accurate and quick identification of faults. Show more

Keywords: Fault tree, fault diagnosis, probabilistic neural networks, rapier loom

DOI: 10.3233/JIFS-233009

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7237-7257, 2023

Authors: Jia, Lifen | Jiang, Jiarui | Li, Dongao | Guo, Fengjia

Article Type: Research Article

Abstract: The knock-out options are considered as path-dependent barrier options that only expire worthless once the value of the underlying asset reaches a specific threshold. The uncertain differential equations are typically used to describe stock fluctuations in uncertain financial markets. In this study, we build a stock model considering floating interest rate based on uncertainty theory. On this basis, we mainly study the pricing scheme of American call and put options. Based on this model, we mainly research the pricing schemes for call and put options with the American barrier option. Moreover, we develope the parameter estimation for the uncertain stock …model and analyze the results of the uncertain hypothesis test. Finally, we design numerical algorithms for the corresponding option pricing formulas. As an application, we verify the validity of the formulas through numerical experiments. Show more

Keywords: Barrier option, option pricing, stock model, floating interest rate, parameter estimation

DOI: 10.3233/JIFS-233634

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7259-7270, 2023

Authors: Liu, Yefei

Article Type: Research Article

Abstract: Sports news is a type of discourse that is characterized by a specific vocabulary, style, and tone, and it is typically focused on conveying information about sporting events, athletes, and teams. Thematic context-based deep learning is a powerful approach that can be used to analyze and interpret various forms of natural language, including the discourse expression of sports news. An application model of sign language and lip language recognition based on deep learning is proposed to facilitate people with hearing impairment to easily obtain sports news content. First, the lip language recognition system is constructed; next, MobileNet lightweight network combined …with Long-Short Term Memory (LSTM) is used to extract lip reading features. ResNet-50 residual network structure isadopted to extract the features of sign language; finally, the convergence, accuracy, precision and recall of the model are verified respectively. The results show that the loss of training set and test set converges gradually with the increase of iteration times; the lip language recognition model and the sign language recognition model basically tend to be stable after 14 iterations and 12 iterations, respectively, suggesting a better convergence effect of sign language recognition. The accuracy of sign language recognition and lip language recognition is 98.9% and 87.7%, respectively. In sign language recognition, the recognition accuracy of numbers 1, 2, 4, 6 and 8 can reach 100%. In lip language recognition, the recognition accuracy of numbers 2, 3 and 9 is relatively higher. This exploration can facilitate hearing-impaired people to quickly obtain the relevant content in sports news videos, and also provide help for their communication. Show more

Keywords: Deep learning, sports news, thematic context, feature recognition

DOI: 10.3233/JIFS-230528

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7271-7283, 2023

Authors: Fan, Chunxiao | Yan, Zhen | Wu, Yuexin | Qian, Bing

Article Type: Research Article

Abstract: Dense passage retrieval is a popular method in information retrieval recently, especially in open domain question answering. It aims to retrieve related articles from massive passages to answer the question. Retriever can increase retrieval speed with less loss of accuracy compared to other methods. However, the pretrained language models used in recent research are often ineffective in semantic embedding, which will reduce accuracy. In addition, we find that contrastive learning will diverge the representation space, and Siamese models with independent parameters on both sides will decrease generalization performance. Therefore, we propose span prompt dense passage retrieval (SPDPR) based on span …mask prompt tuning and parameter sharing in Chinese open-domain dense retrieval. This model can generate more efficient representation embeddings and effectively counteract the separation tendency between positive samples. We evaluate the effectiveness of SPDPR in DYKzh, as well as two Chinese datasets. SPDPR surpasses all SOTAs implemented in DYKzh and achieves a competitive result in other datasets. Show more

Keywords: Dense retrieval, prompt tuning, question answering, natural language processing

DOI: 10.3233/JIFS-231328

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7285-7295, 2023

Authors: Wu, Yixiang

Article Type: Research Article

Abstract: Cultural and creative products are empowered through cultural connotation in the market with ever-changing customer needs. Analyzing user preferences and matching them with product design elements has become the focus of research. Taking ceramic bracelet as the research example, this study proposed an evolutionary system which integrates the interactive genetic algorithm with artificial neural network and fuzzy analytic hierarchy process based on evaluation grid method. First, the cultural genes were extracted from cultural products as the design elements. Second, the attractiveness characteristics of the products and customer demand dimension information were analyzed by evaluation grid method. Third, the fuzzy analytic …hierarchy process was used to assign weight values to the 3 users’ perceptual evaluation vocabularies. Fourth, the artificial neural network algorithm was incorporated into the fitness evaluation stage of the interactive algorithm to reduce information distortion caused by evaluation fatigue. Finally, after training the samples using the back propagation neural network, 8 design schemes with a fitness value exceeding 4.5 were obtained. The iterative curve indicated that after the 51st generation, the error accuracy approached 0.09. The experimental results verified that the system could help to improve the efficiency of product design, and design products that are more in line with user needs. Show more

Keywords: Cultural and creative product, interactive genetic algorithm, evaluation grid method

DOI: 10.3233/JIFS-231906

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7297-7315, 2023

Authors: Dinçer, Hasan | Eti, Serkan | Yüksel, Serhat | Özdemir, Sümeyye | Yílmaz, Ahmet Enes | Ergün, Edanur

Article Type: Research Article

Abstract: The purpose of this study is to identify the key factors to minimize carbon emission problem. Within this framework, an examination has been made by considering both data mining and fuzzy decision-making techniques. In the analysis process, N-gram methodology is implemented to the abstracts of 1711 studies in the “Sciencedirect” platform and five different indicators are selected. In the proposed decision-making model, firstly, selected criteria are weighted by Spherical fuzzy CRITIC. Secondly, E7 economies are ranked with RATGOS. Thirdly, a sensitivity analysis is performed, and a comparative evaluation is conducted by MAIRCA technique. The most important originality of this proposed …model is generating a new technique named RATGOS. In the literature, there are various decision-making models to rank the alternatives. However, lots of researchers criticized these approaches due to some reasons, such as using Euclidean distance by calculating the distances to the negative ideal solutions. Thus, it is seen that there is a need for a new technique that considers geometric mean in proportional concepts. To reach this objective, the RATGOS technique is introduced so that it can be possible to reach more accurate results. The findings indicate that renewable energy usage is the most critical item to overcome carbon emission problem. Therefore, some measures should be taken to increase renewable energy investments. First, governments can offer incentives for renewable energy investments. These incentives may include various incentives such as tax exemptions and low interest loans. Moreover, more research and development works are required for the development of renewable energy technologies. In this way, it can make renewable energy technologies more effective and efficient. For future research directions, an evaluation can be carried out for developed countries because carbon emissions problem also plays a crucial role for the social and economic improvements of these economies. Show more

Keywords: Spherical fuzzy sets, CRITIC, RATGOS, TOPSIS, carbon emission, sustainable economic development

DOI: 10.3233/JIFS-232303

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7317-7333, 2023

Authors: Khan, Vakeel A. | Rahaman, SK Ashadul | Hazarika, Bipan | Alam, Masood

Article Type: Research Article

Abstract: In this paper, we address some imprecisions in the definition of neutrosophic normed space proposed by Kirişçi and Şimşek [16 ], Definition 4. We propose a modification to the definition and introduce the notion of rough lacunary statistical convergence in the neutrosophic normed space. Furthermore, we present the idea of rough lacunary statistical cluster points in neutrosophic normed spaces and investigate the relationship between the set of these cluster points and the set of rough lacunary statistical limit points of the aforementioned convergence.

Keywords: Neutrosophic normed space, statistical convergence, rough convergence, rough lacunary statistical convergence

DOI: 10.3233/JIFS-222548

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7335-7351, 2023