Journal of Intelligent & Fuzzy Systems - Volume 45, issue 6

Authors: Xia, Wenxin | Che, Jinxing

Article Type: Research Article

Abstract: Wind energy needs to be used efficiently, which depends heavily on the accuracy and reliability of wind speed forecasting. However, the volatility and nonlinearity of wind speed make this difficult. In volatility and nonlinearity reduction, we sequentially apply complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and variational mode decomposition (VMD) to secondarily decompose the wind speed data. This framework, however, requires effectively modeling multiple uncertainty components. Eliminating this limitation, we integrate crow search algorithm (CSA) with deep belief network (DBN) to generate a unified optimal deep learning system, which not only eliminates the influence of multiple uncertainties, but …also only adopts DBN as a predictor to realize parsimonious ensemble. Two experiments demonstrate the superiority of this system. Show more

Keywords: Parsimonious ensemble, secondary decomposition, optimal deep learning, crow search algorithm

DOI: 10.3233/JIFS-233782

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10799-10822, 2023

Authors: Kumari, Ritika | Singh, Jaspreeti | Gosain, Anjana

Article Type: Research Article

Abstract: Class imbalance problem (CIP) exists when the class distribution is not uniform. Many real-world scenarios face CIP which attracted the researcher’s attention to this problem. Training machine learning (ML) models with class imbalanced datasets is a challenging problem. Ensemble methods in ML involve training multiple classifiers, combining or averaging their predictions to come to a final prediction. Specifically designed ensemble-based methods can overcome the difficulty faced by traditional classifiers and can handle the CIP. The performance of 19 ensemble methods for 44 unbalanced datasets is assessed in this paper in order to observe the effects of the class imbalance ratio …(CIR). For performance evaluation, we divide these datasets into three categories, i.e., Slightly Imbalance (SI), Moderately Imbalance (MI) and Highly Imbalance (HI) based on CIR. With the proposed perspective, we observe that different ensemble methods perform well in different categories suggesting that the percentage of minority or majority class could be a criterion for the selection of ensemble methods for class imbalance datasets. Moreover, visual representations and different non-parametric statistical tests are also used to have more reliable results. Show more

Keywords: Ensemble methods, boosting, bagging, hybrid approaches, classification

DOI: 10.3233/JIFS-223333

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10823-10834, 2023

Authors: Koshti, Dipali | Gupta, Ashutosh | Kalla, Mukesh

Article Type: Research Article

Abstract: Visual question Answering (VQA) is a computer vision task that requires a system to infer an answer to a text-based question about an image. Prior approaches did not take into account an image’s positional information or the questions’ grammatical and semantic relationships during image and question processing. Featurization, which leads to the false answering of the question. Hence to overcome this issue CNN –Graph based LSTM with optimized BP Featurization technique is introduced for feature extraction of image as well as question. The position of the subjects in the image has been determined using CNN with a dropout layer and …the optimized momentum backpropagation during the extraction of image features without losing any image data. Then, using a graph-based LSTM with loopy backpropagation, the questions’ syntactic and semantic dependencies are retrieved. However, due to their lack of external knowledge about the input image, the existing approaches are unable to respond to common sense knowledge-based questions (open domain). As a result, the proposed Spatial GCNN knowledge retrieval with PDB Model and Spatial Graph Convolutional Neural Network, which recovers external data from Wikidata, have been used to address the open domain problems. Then the Probabilistic Discriminative Bayesian model, based Attention mechanism predicts the answer by referring to all concepts in question. Thus, the proposed method answers the open domain question with high accuracy of 88.30%. Show more

Keywords: Visual Question Answering, graph-based LSTM, SVO triples sentence, Discriminative Bayesian model, dynamic memory network

DOI: 10.3233/JIFS-230198

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10835-10852, 2023

Authors: My, Bui T.T. | Ta, Bao Q.

Article Type: Research Article

Abstract: Credit scoring is a typical example of imbalanced classification, which poses a challenge to conventional machine learning algorithms and statistical classifiers when attempting to accurately predict outcomes for defaulting customers. In this paper, we propose a credit scoring classifier called Decision Tree Ensemble model (DTE). This model effectively addresses the challenge of imbalanced data and identifies significant features that influence the likelihood of credit status. An experiment demonstrates that DTE exhibits superior performance metrics in comparison to well-known based-tree ensemble classifiers such as Bagging, Random Forest, and AdaBoost, particularly when integrated with resampling techniques for handling imbalanced data.

Keywords: Classifiers, credit scoring, decision tree, ensemble classifiers, imbalanced data

DOI: 10.3233/JIFS-230825

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10853-10864, 2023

Authors: Catherine Grace John, J. | Deepika, M. | Elavarasan, B.

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-232591

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10865-10872, 2023

Authors: Thumilvannan, S. | Balamanigandan, R.

Article Type: Research Article

Abstract: The survival of patients’ deaths owing to Heart Disease (HD) could be improved with the assistance of an enhanced approach for predicting the risk of diabetes and HD. Nevertheless, such schemes are developed rarely. Thus, this paper proposes a new Power Lognormal Distribution-Semi-Supervised Learning-centric Restricted Boltzmann Machine (PLD-SSL-RBM) diabetes and HD risk level prediction model for IoT data. The missing data are removed by partial Derivation of the Hamilton-Cluster Centered-K-means Clustering (DH-CC-KC) to efficiently train the classifier and then, the data are aggregated. Next, to reduce the dataset size, the features are reduced with Shell Sort-Principal Component Analysis (SS-PCA). Then, …the fuzzy rule-based decisions are created with the T -test-centric Uniform Distribution-Elephant Herd Optimization Algorithm (T -test-UDEHOA) Correlated Features (CF) to classify the risk levels accurately. Lastly, the risk levels of HD and diabetes are predicted; in addition, by employing the Elliptic Curve Cryptography (ECC)7encryption technique, the data is securely stored on the medical database. The proposed risk prediction model’s performance is analyzed on the Framingham dataset. As per the experimental outcomes, when analogized to the prevailing methodologies, the proposed technique attained a higher accuracy of 99.55%. Show more

Keywords: Internet of Things (IoT), heart disease and diabetes risk, Restricted Boltzmann Machine (RBM), correlated features, Elephant Herd Optimization Algorithm (EHOA), Correlated Feature (CF)

DOI: 10.3233/JIFS-232851

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10873-10886, 2023

Authors: Thakur, Divya | Lalwani, Praveen

Article Type: Research Article

Abstract: The use of mobile devices has contributed greatly to the expansion of Human Activity Recognition (HAR) studies in recent years. Researchers find it attractive because of its versatility, low cost, compact size, ease of usage, and wide range of possible applications. Conventional, biological, and control-based systems are just some of the methods that have been created for humanoid robot movement in recent years. This article specifically targeted improvement in the proposed method, which is different from previous papers. This is being done with the use of the publicly available Human Activity Gait (HAG) data set, which documents a wide range …of different types of activities. IMU sensors were used to collect this data set. Several experiments were conducted using different machine-learning strategies, each with its own set of hyper-parameters, to determine how best to utilize these data. In our proposed model Cuckoo Search Optimization is being used for optimum feature selection. On this data set, we have tested a number of machine learning models, including LR, KNN, DT, and proposed CSOEM (Cuckoo Search-Based Optimized Ensemble Model). The simulation suggests that the proposed model CSOEM achieves an impressive accuracy of 98%. This CSOEM is built by combining the feature selection strategy of Cuckoo Search Optimizations with the ensembling of the LR, KNN, and DT. Show more

Keywords: Bipedal robot locomotion, CSO: cuckoo search optimization, HAG: human activity gait, HAR: human activity recognition

DOI: 10.3233/JIFS-232986

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10887-10900, 2023

Authors: Lian, Jing | Chen, Shi | Pi, Jiahao | Li, Linhui | Li, Qingfeng

Article Type: Research Article

Abstract: Localization through intricate traffic scenes poses challenges due to their dynamic, light-variable, and low-textured nature. Existing visual Simultaneous Localization and Mapping (SLAM) methods, which are based on static and texture-rich assumptions, struggle with drift and tracking failures in such complex environments. To address this, we propose a visual SLAM algorithm based on semantic information and geometric consistency in order to solve the above issues and further realize autonomous driving applications in road environments. In dynamic traffic scenes, we employ an object detection network to identify moving objects and further classify them based on geometric consistency as dynamic objects or potential …dynamic objects. This method permits us to preserve more reliable static feature points. In low-texture environments, we propose a method that employs key object categories and geometric parameters of static scene objects for object matching between consecutive frames, effectively resolving the problem of tracking failure in such scenarios. We conducted experiments on the KITTI and ApolloScape datasets for autonomous driving and compared them to current representative algorithms. The results indicate that in the dynamic environment of the KITTI dataset, our algorithm improves the compared metrics by an average of 29.68%. In the static environment of the KITTI dataset, our algorithm’s performance is comparable to that of the other compared algorithms. In the complex traffic scenario R11R003 from the ApolloScape dataset, our algorithm improves the compared metrics by an average of 25.27%. These results establish the algorithm’s exceptional localization accuracy in dynamic environments and its robust localization capabilities in environments with low texture. It provides development and support for the implementation of autonomous driving technology applications. Show more

Keywords: Autonomous vehicles, SLAM, traffic environments, object detection

DOI: 10.3233/JIFS-233068

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10901-10919, 2023

Authors: Liu, Zhichao | Wang, Yachao | Ma, Zhiyuan | Cao, Mengnan | Liu, Mingda | Yang, Xiaochu

Article Type: Research Article

Abstract: Real-time monitoring of electricity usage details through load monitoring techniques is a crucial aspect of smart power grid management and monitoring, allowing for the acquisition of information on the electricity usage of individual appliances for power users. Accurate detection of electricity load is essential for refined load management and monitoring of power supply quality, facilitating the improvement of power management at the user side and enhancing power operation efficiency. Non-intrusive load monitoring (NILM) techniques require only the analysis of total load data to achieve load monitoring of electricity usage details, and offer advantages such as low cost, easy implementation, high …reliability, and user acceptance. However, with the increasing number of distributed new load devices on the user side and the diversification of device development, simple load recognition algorithms are insufficient to meet the identification needs of multiple devices and achieve high recognition accuracy. To address this issue, a non-intrusive load recognition (NILR) model that combines an adaptive particle swarm optimization algorithm (PSO) and convolutional neural network (CNN) has been proposed. In this model, pixelated images of different electrical V-I trajectories are used as inputs for the CNN, and the optimal network layer and convolutional kernel size are determined by the adaptive PSO optimization algorithm during the CNN training process. The proposed model has been validated on the public dataset PLAID, and experimental results demonstrate that it has achieved a overall recognition accuracy of 97.26% and F-1 score of 96.92%, significantly better than other comparison models. The proposed model effectively reduces the confusion between various devices, exhibiting good recognition and generalization capabilities. Show more

Keywords: Smart grid, non-intrusive load recognition, DL, Convolutional Neural Network, adaptive Particle Swarm Optimization

DOI: 10.3233/JIFS-233813

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10921-10935, 2023

Authors: Afzali, Parvaneh | Rezapour, Abdoreza | Rezaee Jordehi, Ahmad

Article Type: Research Article

Abstract: Handwriting is an individual trait that serves as evidence to authenticate a particular writer. Identifying the writer of a handwritten text has shown encouraging results in examining historical and forensic documents. In this paper, we propose a novel offline writer identification system based on the challenging analysis of small amount of data to extract distinct patterns. In our deep network, the feature extraction process relies on a specially designed dual-path architecture, and the resulting embeddings are concatenated to produce the final learned features. To deal with a variety of uncertainties such as high intra-class variations and noises, we leverage the …fuzzy logic in the design of a custom Convolutional Neural Network (CNN) with a type-2 fuzzy activation function for the first path. Additionally, the second path utilizes the transfer learning-based CNN to enhance the discriminability of the learned features. Our method allows for text-independent writer identification, eliminating the need for identical handwriting samples to train and test the model. Considering that various factors can influence the handwriting style, a dataset containing right-to-left handwriting samples is assembled. The proposed method is evaluated on our developed dataset and four widely-known public datasets, namely KHATT, CVL, Firemaker, and IAM. High accuracy values are achieved, with results of 99.85%, 99.83%, 99.79%, 99.64%, and 98.17% for each dataset, respectively. One noteworthy aspect of this study is that the evaluation results on diverse datasets demonstrate the applicability of the proposed model to various languages. Moreover, the model performs effectively in real-world scenarios with limited handwritten data. Show more

Keywords: Writer identification, convolutional neural networks, Type-2 fuzzy logic, deep feature concatenation

DOI: 10.3233/JIFS-231889

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10937-10949, 2023