Journal of Intelligent & Fuzzy Systems - Volume Pre-press, issue Pre-press

Authors: Jian-min, Qiao | Wo-yuan, Li

Article Type: Research Article

Abstract: The research work on two-sided matching decision problem considering interval triangular fuzzy information is very scarce, and it needs to be further studied. Based on this, this paper proposes a two-sided matching model based on interval triangular fuzzy sets, with the background of the two-sided matching problem in the interval triangular fuzzy set environment. Firstly, the theory of two-sided matching and interval triangular fuzzy sets is given; Secondly, the comprehensive mean value formula is defined, and the interval triangular fuzzy evaluation matrix is transformed into the comprehensive mean value matrix by using the comprehensive mean value formula; Thirdly, a two-sided …matching model is built with the goal of maximizing the satisfaction of each subject; Finally, the feasibility and effectiveness of the proposed method are verified by examples of investment fund institutions and financing enterprises. Show more

Keywords: Interval triangular fuzzy set, Integrated mean, two-sided matching

DOI: 10.3233/JIFS-222108

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2022

Authors: Zhang, Yangjingyu | Cai, Qiang | Wei, Guiwu | Chen, Xudong

Article Type: Research Article

Abstract: Based on the traditional TOPSIS method and 2-tuple linguistic Pythagorean fuzzy numbers (2TLPFNs), this paper builds a novel 2TLPF-TOPSIS method that combines cumulative prospect theory (CPT) to cope with the multiple attribute group decision-making (MAGDM). This new method takes into account the decision-makers’ mind and the uncertainty of decision-making, and is more in line with the real decision-making environment. First, this paper briefly reviews some necessary theories related to PFS, as well as the calculation rules and comparison methods of 2TLPFNs. Then, since there is often subjective randomness when determining the weight, the entropy method is utilized to objectively determine …the weight. After that, give the specific calculation steps of the new method. In order to show the effectiveness of the new method, apply it into a specific numerical example about evaluating airline business operations capability, and compare it with the other four different methods. The ranking results depict that the new method designed is effective and reasonable, and has good application value of MAGDM problems. Show more

Keywords: Multiple attribute group decision making (MAGDM), 2-tuple linguistic Pythagorean fuzzy numbers (2TLPFNs), TOPSIS method, cumulative prospect theory (CPT), airline business operations capability

DOI: 10.3233/JIFS-220776

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2022

Authors: Noor Mohamed, Sheerin Sitara | Srinivasan, Kavitha

Article Type: Research Article

Abstract: Recent technological developments and improvement in the medical domain demands advancement, to address the issue of early disease detection. Also, the current pandemic has resulted in considerable progress of improvement in the medical domain, through online consultation by physicians for different diseases using clinical reports and medical images. A similar process is adopted in developing a Visual Question Answering (VQA) system in the medical field. In this paper, existing medical VQA datasets, appropriate techniques, suitable quantitative metrics, real time challenges and, the implementation of one VQA approach with algorithms and performance evaluation are discussed. The medical VQA datasets collected from …multiple sources are represented in different perspectives (organwise, planewise, modality-type and abnormality-type) for a better understanding and visualization. Then the techniques used in VQA are subsequently grouped and explained, based on evolution, complexity in the dataset and the need for semantics in understanding the questions. In addition, the implementation of a VQA approach using VGGNet and LSTM is carried out for existing and improved datasets, and analyzed with accuracy and BLEU score metrics. The improved datasets, created through dataset reduction and augmentation approaches, resulted in better performance than the existing datasets. Finally, the challenges of the medical VQA domain are examined in terms of datasets, combining techniques, and modifying the parameters of existing performance metrics for future research. Show more

Keywords: Visual question answering, medical VQA, ImageCLEF, VQA-MED dataset, VQA-RAD dataset, VGGNet, LSTM, challenges of VQA

DOI: 10.3233/JIFS-222569

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2022

Authors: Zhang, Xiaolu | Wan, Jun | Luo, Ji

Article Type: Research Article

Abstract: Interval-valued q-rung orthopair fuzzy number (IVq-ROFN) is a popular tool for modeling complex uncertain information and has gained successful applications in the field of comprehensive evaluation. However, most of the existing studies are based on the absolute values of evaluation data but fail to take incentive effects into account. Reasonable and appropriate incentive can guide the evaluated objects to better achieve the decision goals. Therefore, this study develops an incentive mechanism-based interval-valued q-rung orthopair fuzzy dynamic comprehensive evaluation method. Firstly, new interval-valued q-rung orthopair fuzzy measures including deviation measure and correlation coefficient are proposed for managing IVq-ROFNs data. To overcome …the limitations of the existing aggregating operators that are not suitable for scenarios with need of many times of data aggregation, we introduce two new interval-valued q-rung orthopair fuzzy aggregating operators. Furthermore, a new interval-valued orthopair fuzzy CRITIC method is developed to objectively determine the importance of the evaluated criteria. More importantly, the horizontal incentive effects within a single period and the vertical incentive effects during multiple periods under IVq-ROFNs environments are proposed to reward (or punish) the evaluated objects in the evaluation process. The evaluated results are determined based on the full compensatory model and the multiplicative form model. The main advantage of the developed method is that the expectations of decision-makers and the dynamic characteristics during multiple periods are taken fully into account, which can make the evaluation results more reasonable and reliable. Finally, this developed comprehensive evaluation method is applied to evaluate the green development level of Jiangxi province within eleven cities from 2016 to 2020. We observe that the cities x 2 , x 3 , x 4 , x 5 , x 7 , x 8 are rewarded within positive incentive values and the cities x 1 , x 6 , x 9 , x 10 , x 11 are punished within negative incentive values. Especially, the positive incentive value for the city x 3 is the biggest and the negative incentive value for the city x 9 is the biggest. The best city in term of GDL is x 3 . The evaluated results with consideration of incentive effects are in line with the expectation of the decision-maker. Show more

Keywords: Interval-valued q-rung orthopair fuzzy number, Comprehensive evaluation, CRITIC, Incentive effect, Green development level

DOI: 10.3233/JIFS-222505

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2022

Authors: Hu, Danhui | Huang, Zeqi | Yin, Kan | Li, Feng

Article Type: Research Article

Abstract: Considering that the operation of power transmission and transformation equipment is not timely discovered due to the untimely data integration, a multi-dimensional heterogeneous data clustering algorithm for power transmission and transformation equipment based on multimodal deep learning is proposed. The multi-modal deep learning method is used to mine relevant data and measure the similarity between the data, which can improve the accuracy of subsequent multi-bit heterogeneous data clustering of power transmission and transformation equipment. Set up a clustering center and process data clustering to complete multi-dimensional heterogeneous data clustering of power transmission and transformation equipment. The experimental results show that …the method has high clustering accuracy in the clustering of voltage deviation overrun times, voltage harmonic total distortion rate overrun times, and voltage flicker overrun times. Show more

Keywords: Multimodal deep learning, power transmission and transformation equipment, heterogeneous data, clustering, mining, similarity

DOI: 10.3233/JIFS-222924

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-8, 2022

Authors: Chalasani, Rama Devi | Radhika, Y.

Article Type: Research Article

Abstract: ITK inhibitor is used for the treatment of asthma and activity of inhibitor prediction helps to provide better treatment. Few researches were carried out for the analysis and prediction of kinases activity. Existing methods applied for the inhibitor prediction have limitations of imbalance dataset and lower performance. In this research, the Posterior Probabilistic Weighted Average Based Ensemble voting (PPWAE)ensemble method is proposed with various classifier for effective prediction of kinases activity. The PPWAE model selects the most probable class from the classification method for prediction. The co-train model has two advantages: Features are trained together to increases the learning rate …of model and probability is measured for each model to select the efficient classifier. Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Classification and Regression Tree (CART), and Nave Bayes were among the classifiers employed. The results suggest that the Probabilistic Co-train ensemble technique performs well in kinase activity prediction. In the prediction of ITK inhibitor activity, the suggested ensemble method has a 74.27 percent accuracy, while the conventional SVM method has a 60% accuracy. Show more

Keywords: Decision tree, ITK inhibitor, posterior probabilistic weighted average based ensemble voting, random forest, support vector machine

DOI: 10.3233/JIFS-221412

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-10, 2022

Authors: Deng, Yu

Article Type: Research Article

Abstract: The competitiveness evaluation of regional financial centers is frequently looked as the multiple attribute group decision-making (MAGDM) problem. Based on the TODIM method and fuzzy number intuitionistic fuzzy sets (FNIFS), this paper proposes a new FNIF-TODIM method to evaluate the competitiveness of regional financial centers. First, some basic theories related to FNIFS are briefly introduced. In addition, the weights of the attributes are obtained objectively using the CRITIC weighting method. Then, the traditional TODIM method is extended to FNIFS to obtain the final order of alternatives. As a result, all alternatives can be ranked and the best one for the …competitiveness assessment of regional financial centers can be identified. Finally, an example for competitiveness evaluation of regional financial centers and some decision comparative analysis is listed. The results show that the established algorithmic approach is useful. The main works of this work are: (1) the paper constructs the FNIF-TODIM method for the evaluation of the competitiveness of regional financial centers; (2) the established method is illustrated by a case study for competitiveness evaluation of regional financial centers; and (3) some comparisons prove the rationality and advantages. Show more

Keywords: Multiple attribute group decision making (MAGDM), fuzzy number intuitionistic fuzzy sets (FNIFSs), TODIM method, CRITIC method, Competitiveness evaluation

DOI: 10.3233/JIFS-221247

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2022

Authors: Ashok Kumar, L. | Karthika Renuka, D. | Saravana Kumar, S.

Article Type: Research Article

Abstract: Human-wildlife conflicts in the habitats along the forest fringes are a substantial issue. An automated monitoring system that can find animal breaches and deter them from foraging fields is essential to solve this conflict. However, automatically forefending the intruding animals is a challenging task. In this paper, we propose a deep learning model for elephant identification using YOLO lite with knowledge distillation which could be easily deployed in edge devices. We also propose an elephant re-identification system using Siamese network which is helpful in tracking the number of times the elephant tries to forage the field. This re-encounter information about …the same elephant can be used to decide the averting sound for the particular elephant. The proposed system is found to show an accuracy of 89%, which is provides good performance improvement when compared to the state of art models proposed for animal identification. Thus the proposed lite weight knowledge distillation based animal identification model and deep learning based animal re-identification model can be employed in edge devices for real time monitoring and animal deterring to safe guard the farm fields. Show more

Keywords: Neural networks, knowledge distillation, siamese neural network, classification, re-identification, computer vision

DOI: 10.3233/JIFS-222672

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2022

Authors: Zhang, Sumin | Ye, Jun

Article Type: Research Article

Abstract: Group decision-making is that individuals collectively make a choice from a set of alternatives. Then, in complex decision-making problems, the decision-making process is no longer subject to a single individual, but group decision-making. Hence, the decision reliability and credibility of the collective evaluation information become more critical. However, current decision-making methods lack the confidence level and credibility measure of group evaluation information. To ensure the confidence level and credibility measure of small-scale group decision-making problems, the aim of this paper is to propose a Multi-Attribute Group Decision-Making (MAGDM) approach using a hyperbolic sine similarity measure between Confidence Neutrosophic Number Credibility …Sets (CNNCSs) in the circumstance of Fuzzy Credibility Multi-Valued Sets (FCMVSs). To achieve this aim, this paper contains the following works. First, we present FCMVS to represent the mixed information of fuzzy sequences and credibility degree sequences with different and/or identical fuzzy values. Second, according to the normal distribution and confidence level of fuzzy values and credibility degrees in FCMVS, FCMVS is transformed into CNNCS to avoid the operational issue between different fuzzy sequence lengths in FCMVSs and to ensure the confidence neutrosophic numbers/confidence intervals of fuzzy values and credibility degrees. Third, a hyperbolic sine similarity measure of CNNCSs is established in the circumstance of FCMVSs. Fourth, a MAGDM approach is developed based on the weighted hyperbolic sine similarity measure in the circumstance of FCMVSs. Fifth, the proposed MAGDM approach is applied to an actual example of the equipment supplier choice problem to illustrate the efficiency and rationality of the proposed MAGDM approach in a FCMVS circumstance. In general, this study reveals new contributions in the representation, transformation method, and similarity measure of small-scale group assessment information, as well as the proposed MAGDM method subject to the normal distribution and confidence levels in small-scale MAGDM scenarios. Show more

Keywords: Fuzzy credibility multi-valued set, confidence neutrosophic number credibility set, hyperbolic sine similarity measure, group decision making

DOI: 10.3233/JIFS-223065

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2022

Authors: Wu, Chun | Yang, Liu

Article Type: Research Article

Abstract: A unique approach for assessing the compressive strength (CS ) of high-performance concrete (HPC ) incorporating blast furnace slag (BFS ) and fly ash (FA ) has been created using support vector regression (SVR ) analytics. In order to identify crucial SVR methodology variables that could be adjusted for improved performance, the Henry gas solubility optimization (HGSO ) and Cuckoo search optimization (CSO ) algorithms were both employed in this study. The recommended methods were developed utilizing 1030 experiments and eight inputs, including the CS as the forecasting objective, admixtures, aggregates, and curing age as the main mix …design component. The results were then contrasted with those from related literature. The estimate results suggest that combined HGSO-SVR and CSO-SVR analysis might perform extraordinarily well in estimating. The Root mean square error value for the HGSO  - SVR decreased remarkably when compared to the CSO  - SVR . As can be seen from the comparisons, the HGSO  - SVR that was built beats anything previously published. In conclusion, the suggested HGSO  - SVR analysis might be determined as the proposed system for forecasting the CS of HPC improved with FA and BFS . Show more

Keywords: High-performance concrete, Compressive strength, fly ash, blast furnace slag, estimation, SVR, HGSO, COA

DOI: 10.3233/JIFS-222348

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2022