Journal of Intelligent & Fuzzy Systems - Volume 44, issue 2

Authors: Saraswathi, Meera | Meera, K.N.

Article Type: Research Article

Abstract:  A radio mean labeling l of G maps distinct vertices of G to distinct elements of ℤ + satisfying the radio mean condition that diam ( G ) + 1 - d G ( w , w ′ ) ≤ ⌈ l ( w ) + l ( w ′ ) 2 ⌉ , ∀ w , w ′ ∈ V ( G ) where d G  (w , w ′) is the smallest length of a …w , w ′- path in G and diam  (G ) = max {d G  (w , w ′) : w , w ′ ∈ V  (G )} is the diameter of G . The radio mean number of graph G is defined as rmn  (G ) = min {span  (l ) : l  isaradiomeanlabelingof G } where span (l ) is given by max {l  (w ) : w  ∈ V  (G )}. It has been proved in literature that |V  (G ) | ≤ rmn  (G ) ≤ |V  (G ) | + diam  (G ) -2. Cryptographic algorithms can exploit the unique radio mean number associated with a graph to generate keys. An exhaustive listing of all feasible radio mean labelings and their span is essential to obtain the radio mean number of a given graph. Since the radio mean condition depends on the distance between vertices and the graph’s diameter, as the order and diameter increase, finding a radio mean labeling itself is quite difficult and, so is obtaining the radio mean number of a given graph. Here we discuss the extreme values of the radio mean number of a given graph of order n . In this article we obtained bounds on the radio mean number of a graph G of order n and diameter d in terms of the radio mean number of its induced subgraph H where diam  (H ) = d and d H  (w , w ′) = d G  (w , w ′) for any w , w ′ ∈ V  (H ). The diametral path P d +1 is one such induced subgraph of G and hence we have deduced the limits of rmn  (G ) in terms of rmn  (P d +1 ). It is known that if d  = 1,  2 or 3, then rmn  (G ) = n . Here, we have given alternative proof for the same. The authors of this article have studied radio mean labeling of paths in another article. Using those results, we have improved the bounds on the radio mean number of a graph of order n and diameter d  ≥ 4. It is also shown that among all connected graphs on n vertices, the path P n of order n possesses the maximum radio mean number. This is the first article that has completely solved the question of maximum and minimum attainable radio mean numbers of graphs of order n . Show more

Keywords: Channel assignment problem, graph labeling, radio labeling, radio mean labeling, radio mean number, paths

DOI: 10.3233/JIFS-221595

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1691-1702, 2023

Authors: Zhou, Lixin | Zhou, Kexin | Liu, Chen

Article Type: Research Article

Abstract: Stance detection is the task of classifying user reviews towards a given topic as either supporting, denying, querying, or commenting (SDQC) . Most approaches for solving this problem use only the textual features, including the linguistic features and users’ vocabulary choice. A few approaches have shown that information from the network structure like graph model can add value, in addition to the textual features, by providing social connections and interactions that may be vital for the stance detection task. In this paper, we present a novel model that combines the text features with the network structure by (1) creating a …graph-structure model based on conversational structure towards specific topics and (2) constructing a tree-gated neural network model (TreeGGNN) to capture structure information among reviews. We evaluate our model on four baseline models, which shows that the combination of text and network can achieve an improvement of 2–6% over the state-of-the-art baselines. Show more

Keywords: Stance detection, gated graph neural network, deep learning, structure of conversation thread

DOI: 10.3233/JIFS-221953

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1703-1714, 2023

Authors: Krishnakumar, S. | Manivannan, K.

Article Type: Research Article

Abstract: The meningioma brain tumor detection is more important than the other tumor detection such as Glioma and Glioblastoma, due to its high severity level. The tumor pixel density of meningioma tumor is high and it leads to sudden death if it is not detected timely. The meningioma images are detected using Modified Empirical Mode Decomposition- Convolutional Neural Networks (MEMD-CNN) classification approach. This method has the following stages data augmentation, spatial-frequency transformation, feature computations, classifications and segmentation. The brain image samples are increased using data augmentation process for improving the meningioma detection rate. The data augmented images are spatially transformed into …frequency format using MEMD transformation method. Then, the external empirical mode features are computed from this transformed image and they are fed into CNN architecture to classify the source brain image into either meningioma or non-meningioma. The pixels belonging tumor category are segmented using morphological opening-closing functions. The meningioma detection system obtains 99.4% of Meningioma Classification Rate (MCR) and 99.3% of Non-Meningioma Classification Rate (NMCR) on the meningioma and non-meningioma images. This MEMD-CNN technique for meningioma identification attains 98.93% of SET, 99.13% of SPT, 99.18% of MSA, 99.14% of PR and 99.13% of FS. From the statistical comparative analysis of the proposed MEMD-CNN system with other conventional detection systems, the proposed method provides optimum tumor segmentation results. Show more

Keywords: Meningioma, tumor, transformation, features, classification rate

DOI: 10.3233/JIFS-222172

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1715-1726, 2023

Authors: Zhang, Shiguang | Yuan, Qiuyun | Yuan, Feng | Liu, Shiqin

Article Type: Research Article

Abstract: Twin proximal support vector regression is a new regression machine designed by using twin support vector machine and proximal support vector regression. In this paper, we use the above models framework to build a new regression model, called the twin proximal least squares support vector regression model based on heteroscedastic Gaussian noise (TPLSSVR-HGN). The least square method is introduced and the regularization terms b 1 2 and b 2 2 are added respectively. It transforms an inequality constraint problem into two simpler equality constraint problems, which not only …improves the training speed and generalization ability, but also effectively improves the forecasting accuracy. In order to solve the parameter selection problem of model TPLSSVR-HGN, the particle swarm optimization algorithm with fast convergence speed and good robustness is selected to optimize its parameters. In order to verify the forecasting performance of TPLSSVR-HGN, it is compared with the classical regression models on the artificial data set, UCI data set and wind-speed data set. The experimental results show that TPLSSVR-HGN has better forecasting effect than the classical regression models. Show more

Keywords: Least squares support vector regression, twin proximal support vector regression, heteroscedastic Gaussian noise, short-term wind-speed forecasting, equality constraint

DOI: 10.3233/JIFS-211631

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1727-1741, 2023

Authors: Guo, Jidong | Jiao, Heyan

Article Type: Research Article

Abstract: Rapid prediction of earthquake casualties is vital to improve the efficiency of emergency rescue and reduce social losses. Using the Delphi process, nine feature attributes affecting post-earthquake casualties are identified. Corresponding membership functions for the feature attributes are established based on fuzzy theory. The objective weights of feature attributes obtained from the entropy technology are applied to modify the subjective weights from Analytical Hierarchy Process (AHP). To expand the size of the case base, a new idea of collecting cases based on seismic intensity scenarios is proposed. A numerical experiment is carried out for all cases in the case base …along the proposed fuzzy Case-Based Reasoning technical route. The average prediction error is only 14.93%. Show more

Keywords: Post-earthquake casualty, fuzzy set, Case-Based Reasoning, prediction

DOI: 10.3233/JIFS-212183

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1743-1753, 2023

Authors: Gong, Shu | Hua, Gang

Article Type: Research Article

Abstract: Graphs and hypergraphs are popular models for data structured representation. For example, traffic data, weather data, and animal skeleton data are all described by graph structures. Interval-valued fuzzy sets change the membership function of general fuzzy sets from single value functions to interval-valued functions, and thus describe the fuzzy attributes of things in terms of fuzzy intervals, which is more in line with the characteristics of fuzzy objectives. This paper aims to define the bipolar interval-valued fuzzy hypergraph to reveal the inner relationship of fuzzy data, and give some characterizations of it. The characteristics of bipolar interval-valued intuitionistic fuzzy hypergraph …and bipolar interval-valued Pythagorean fuzzy hypergraph are studied. In addition, we discuss the characteristics of the bipolar interval-valued fuzzy threshold graph. Finally, some instances are presented as the applications of bipolar interval-valued fuzzy hypergraphs. Show more

Keywords: Hypergraph, bipolar fuzzy set, threshold graph, bipolar interval-valued fuzzy threshold graph

DOI: 10.3233/JIFS-212551

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1755-1767, 2023

Authors: Wang, Sheng | Shi, Yumei | Hu, Chengxiang | Yu, Chunyan | Chen, Shiping

Article Type: Research Article

Abstract: Nowadays, poverty-stricken college students have become a special group among college students and occupied a higher proportion in it. How to accurately identify poverty levels of college students and provide funding is a new problem for universities. In this study, a novel model, which incorporated Random Forest with Principle Components Analysis (RF-PCA), is proposed to predict poverty levels of college students. To establish this model, we collect some useful information is to construct the datasets which include 4 classes of poverty levels and 21 features of poverty-stricken college students. Furthermore, the feature dimension reduction consists of two steps: the first …step is to select the top 16 features with the ranking of feature, according to the Gini importance and Shapley Additive explanations (SHAP) values of features based on Random Forest (RF) model; the second step is to extract 11 dimensions by means of Principle Components Analysis (PCA). Subsequently, confusion metrics and receiver operating characteristic (ROC) curves are utilized to evaluate the promising performance of the proposed model. Especially the accuracy of the model achieves 78.61%. Finally, compared with seven states of the art classification algorithms, the proposed model achieves a higher prediction accuracy, which indicates that the results provide great potential to identify the poverty levels of college students. Show more

Keywords: RF-PCA, poverty levels, feature selection, feature extraction

DOI: 10.3233/JIFS-213114

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1769-1779, 2023

Authors: Zhang, Yong | Chen, Tianzhen | Jiang, Yuqing | Wang, Jianying

Article Type: Research Article

Abstract: Clustering is widely used in data mining and machine learning. The possibilistic c-means clustering (PCM) method loosens the constraint of the fuzzy c-means clustering (FCM) method to solve the problem of noise sensitivity of FCM. But there is also a new problem: overlapping cluster centers are not suitable for clustering non-cluster distribution data. We propose a novel possibilistic c-means clustering method based on the nearest-neighbour isolation similarity in this paper. All samples are taken as the initial cluster centers in the proposed approach to obtain k sub-clusters iteratively. Then the first b samples farthest from the center of …each sub-cluster are chosen to represent the sub-cluster. Afterward, sub-clusters are mapped to the distinguishable space by using these selected samples to calculate the nearest-neighbour isolation similarity of the sub-clusters. Then, adjacent sub-clusters can be merged according to the presented connecting strategy, and finally, C clusters are obtained. Our method proposed in this paper has been tested on 15 UCI benchmark datasets and a synthetic dataset. Experimental results show that our proposed method is suitable for clustering non-cluster distribution data, and the clustering results are better than those of the comparison methods with solid robustness. Show more

Keywords: Clustering, nearest-neighbour isolation similarity, possibilistic c-means, K-means, merging strategy

DOI: 10.3233/JIFS-213502

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1781-1792, 2023

Authors: Wang, Juntao | Kang, Mengna | Fu, Xuesong | Li, Fei

Article Type: Research Article

Abstract: In this paper, we introduce the notion of state monadic residuated lattices and study some of their related properties. Then we prove that the relationship between state monadic algebras of substructural fuzzy logics completely maintains the relationship between corresponding monadic algebras. Moreover, we introduce state monadic filters of state monadic residuated lattice, giving a state monadic filter generated by a nonempty subset of a residuated lattice, and obtain some characterizations of maximal and prime state monadic filters. Finally, we give some characterization of special kinds of state monadic residuated lattices, including simple, semisimple and local state monadic residuated lattices by …state monadic filters. Show more

Keywords: Mathematical fuzzy logic, mondaic residuated lattice, state monadic residuated lattice, state monadic filter

DOI: 10.3233/JIFS-213527

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1793-1805, 2023

Authors: Thangavel, Jayakumar | Chinnaraj, Gnanavel | Chandrasekaran, Gokul | Kumarasamy, Vanchinathan

Article Type: Research Article

Abstract: This paper presents the design and development of Modular Multilevel Inverter (MMI) to reduce Total harmonic distortion (THD) using intelligent techniques towards marine applications. Many researchers have described the additional advantage of inverter control challenges such as voltage imbalance, increasing the number of voltage levels, power quality issues, reducing the number of semiconductors switches and achieving higher efficiency. Under the intelligent techniques, the implementation is carried out with aid of Artificial Neural Networks (ANN), Fuzzy Logic Controller (FLC) and Adaptive Neuro-Fuzzy Inference System (ANFIS) to calculate the modulation index (ma ) and switching angles (θ ) for MMI. Based on …the calculation, it is trained to form a mapping between inputs and outputs for obtaining reduced Total Harmonics Distortion (THD). The objective of the intelligent controller is to control the inverter for regulating the output voltage with lowest THD. The proposed control structure has been estimated and compared for better robustness in terms of switching angle and modulation index with least THD in the inverter. Simulations and prototype models are made to analyze the controller’s performance, for inverter output voltage and harmonics. This proposed system is designed for marine lighting load application. The FPGA performance with all intelligent methods are analyzed by in SPARTAN3E500 FPGA device. Show more

Keywords: Artificial Neural Networks (ANN), Fuzzy Logic Controller (FLC), Adaptive Neuro-Fuzzy Inference System (ANFIS), Modular Multilevel Inverter (MMI), Total Harmonics Distortion (THD)

DOI: 10.3233/JIFS-220190

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 1807-1821, 2023