Journal of Intelligent & Fuzzy Systems - Volume 46, issue 4

Authors: Guo, Yan | Tang, Dezhao | Cai, Qiqi | Tang, Wei | Wu, Jinghua | Tang, Qichao

Article Type: Research Article

Abstract: Under the influence of the coronavirus disease and other factors, agricultural product prices show non-stationary and non-linear characteristics, making it increasingly difficult to forecast accurately. This paper proposes an innovative combinatorial model for Chinese hog price forecasting. First, the price is decomposed using the Seasonal and Trend decomposition using the Loess (STL) model. Next, the decomposed data are trained with the Long Short-term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. Finally, the prepared data and the multivariate influence factors after Factor analysis are predicted using the gated recurrent neural network and attention mechanisms (AttGRU) to obtain the …final prediction values. Compared with other models, the STL-FA-AttGRU model produced the lowest errors and achieved more accurate forecasts of hog prices. Therefore, the model proposed in this paper has the potential for other price forecasting, contributing to the development of precision and sustainable agriculture. Show more

Keywords: Machine learning, precision agriculture, digital agriculture, STL, attentional mechanisms

DOI: 10.3233/JIFS-235843

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9923-9943, 2024

Authors: Chen, Liang-Ching | Chang, Kuei-Hu | Wu, Chia-Heng | Chen, Shin-Chi

Article Type: Research Article

Abstract: Although natural language processing (NLP) refers to a process involving the development of algorithms or computational models that empower machines to understand, interpret, and generate human language, machines are still unable to fully grasp the meanings behind words. Specifically, they cannot assist humans in categorizing words with general or technical purposes without predefined standards or baselines. Empirically, prior researches have relied on inefficient manual tasks to exclude these words when extracting technical words (i.e., terminology or terms used within a specific field or domain of expertise) for obtaining domain information from the target corpus. Therefore, to enhance the efficiency of …extracting domain-oriented technical words in corpus analysis, this paper proposes a machine-based corpus optimization method that compiles an advanced general-purpose word list (AGWL) to serve as the exclusion baseline for the machine to extract domain-oriented technical words. To validate the proposed method, this paper utilizes 52 COVID-19 research articles as the target corpus and an empirical example. After compared to traditional methods, the proposed method offers significant contributions: (1) it can automatically eliminate the most common function words in corpus data; (2) through a machine-driven process, it removes general-purpose words with high frequency and dispersion rates –57% of word types belonging to general-purpose words, constituting 90% of the total words in the target corpus. This results in 43% of word types representing domain-oriented technical words that makes up 10% of the total words in the target corpus are able to be extracted. This allows future researchers to focus exclusively on the remaining 43% of word types in the optimized word list (OWL), enhancing the efficiency of corpus analysis for extracting domain knowledge. (3) The proposed method establishes a set of standard operation procedure (SOP) that can be duplicated and generally applied to optimize any corpus data. Show more

Keywords: Corpus, natural language processing (NLP), technical word, advanced general-purpose word list (AGWL), COVID-19

DOI: 10.3233/JIFS-236635

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9945-9956, 2024

Authors: de Oliveira, Heveraldo R. | Vieira, Antônio Wilson | Santos, Laércio Ives | Filho, Murilo César Osório Camargos | Ekel, Petr Ya. | D’Angelo, Marcos Flávio S.V.

Article Type: Research Article

Abstract: When providing patient care, healthcare professionals often rely on interpreting laboratory and clinical test results. However, their analysis is constrained by human capacity, leading to uncertainties in diagnoses. Machine learning has the potential to evaluate a larger amount of data and identify patterns and relationships that may otherwise go unnoticed. However, popular machine learning algorithms typically require abundant and labeled data, which is not always available. To address this challenge, the adoption of active learning allows for the selection of the most relevant instances for training, reducing the need for extensive labeling. Additionally, fuzzy logic offers the ability to handle …uncertainties. This paper proposes a novel approach that utilizes fuzzy membership functions to transform data as a pre-processing step for active learning. The objective is to approximate similar instances, specifically for the purpose of prediction, thereby minimizing the workload of human experts in labeling data for model training. The results of this study demonstrate the effectiveness of this approach in predicting heart disease and highlight the potential of using membership functions to enhance machine learning models in the analysis of medical information. By incorporating fuzzy logic and active learning, healthcare professionals can benefit from improved accuracy and efficiency in diagnosing and predicting pacients’ health conditions. Show more

Keywords: Active learning, fuzzy logic, cardiovascular diseases

DOI: 10.3233/JIFS-237047

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9957-9973, 2024

Authors: Ma, Xiyin | Li, Jian

Article Type: Research Article

Abstract: In order to ensure the safety of life and property in large buildings, the design of emergency evacuation routes for large buildings based on cloud computing and GIS big data is studied. Combining cloud computing and GIS big data, a command model for emergency evacuation of large buildings is built. Emergency evacuation functions are realized through the access layer, business logic layer, cloud computing layer and data layer. GIS big data of large buildings is stored in the model data layer. GIS geographic data is clustered through the MapReduce based parallel K-means clustering algorithm in the cloud computing layer. After …clustering, the emergency evacuation road network of large buildings is constructed through GIS in the business logic layer. On the road network, the emergency evacuation route selection method combining Dikstra algorithm and ant colony algorithm is used to realize the optimal route selection of emergency evacuation of large buildings. Experiments show that this method can effectively select the best evacuation path in large buildings, and the evacuation speed of the selected path is fast, which can ensure the safety of people in buildings. Show more

Keywords: Cloud computing, GIS big data, large buildings, emergency evacuation route, K-means clustering, ant colony algorithm

DOI: 10.3233/JIFS-237834

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9975-9986, 2024

Authors: Xiao, Yan | Liang, Jinqian

Article Type: Research Article

Abstract: In many real production scenarios, departmental organizations often exhibit a hierarchical structure, where departments cooperate with subordinate departments to optimize resource allocation and maximize their respective benefits. However, due to a lack of information or data, many model parameters in the allocation process cannot be precisely defined. In response to this challenge, an interval n -person hierarchical resource allocation model is proposed to achieve maximum economic benefit in uncertain environments. Based on the concepts of satisfactory degrees of comparing intervals and interval-valued cores of interval-valued n -person cooperative games, an auxiliary nonlinear programming model and method are developed to solve …the interval-valued cores of such cooperative games. The approach explicitly considers the inclusion and/or overlap relations between intervals, whereas the traditional interval ranking method may not guarantee the existence of interval-valued cores. The proposed method offers cooperative opportunities under uncertain conditions. Finally, the feasibility and applicability of the models and methods are demonstrated through a numerical example and comparison with other methods. Show more

Keywords: Hierarchical structure, resource allocation, uncertain environment, interval n-person cooperative game, nonlinear programming model

DOI: 10.3233/JIFS-191941

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9987-9998, 2024

Authors: Chau, Vinh Huy | Vo, Anh Thu | Ngo, Huu Phuc

Article Type: Research Article

Abstract: This paper discusses the use of an improved random forest regression algorithm (RFRA) to predict the total score of powerlifters. The paper collected the age, weight, and total score of multiple powerlifters, and then used an improved RFRA to build a predictive model. The parameters of this model are optimized by a differential squirrel search algorithm. The experimental results show that our proposed method can effectively predict the total score of powerlifters with an error of less than 10%, which can provide a reference for experts and athletes before training or competition.

Keywords: Artificial intelligence, random forest, powerlifting, total score

DOI: 10.3233/JIFS-230032

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9999-10004, 2024

Authors: Li, Guofa | Wang, Jinfu | He, Jialong | Wang, Jili | Hou, Tianwei

Article Type: Research Article

Abstract: The reliability of machine tool components, particularly the tool magazine manipulator, significantly affects the overall performance of the machine tool. To address the challenge of accurately evaluating the manipulator’s health status using a single performance indicator, this study proposes a method that combines Fuzzy Comprehensive Evaluation (FCE) and a Combined Weighting Method (CWM). By considering both subjective and objective factors, this method provides a comprehensive evaluation of the manipulator’s health status, enhancing the accuracy and reliability of the assessment. The method utilizes fuzzy distribution to construct membership matrices for different health levels and adopts the CWM that combines the Entropy …Weight Method (EWM) and Analytic Hierarchy Process (AHP) to determine the combined weights of the health evaluation indices. This approach improves the accuracy and reliability by considering multiple indicators and objectively weighting them based on their importance. The current health status of the manipulator is evaluated using the fuzzy weighted average operator and the maximum membership principle. Moreover, a fault prediction method based on Particle Swarm Optimization (PSO) and GM(1,1) is proposed to overcome the information gap and small sample problems. The proposed model’s prediction accuracy is verified by comparing it with other models, demonstrating its effectiveness and reliability. Show more

Keywords: Health status evaluation, fault prediction, fuzzy comprehensive evaluation, grey model, particle swarm optimization

DOI: 10.3233/JIFS-233028

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 10005-10018, 2024

Authors: Zhang, Min

Article Type: Research Article

Abstract: Vehicle safety on roadsides is vital for preventing collisions, controlling failures and accidents, and ensuring driver and passenger wellness. Finite Element Analysis (FEA) in vehicle safety relies on the vehicle’s physical attributes for predicting and preventing collisions. This article introduces a Differential FEA (DFEA) model for predicting vehicle collisions regardless of the speed and direction for driver/ passenger safety. The proposed model induces a vehicle’s speed, direction, and displacement from two perspectives: self and approaching vehicle. The collision probability with the trailing or persuading vehicle is calculated by distinguishing the forward and rear features. The differential calculus for the point …of deviation and distance metrics are significantly estimated for a vehicle’s front and rear ends. Such calculus generates a maximum and minimum possibility for self and approaching vehicle contact. This contact is further split based on the collision threshold; the threshold is determined using the safe distance between two vehicles for collision-less driving. The threshold exceeding vehicles are alerted for their change in direction/ speed through contact point (rear/front) differential derivatives. This ensures collision detection under fewer contact errors, leveraging the safety of the duo vehicles. Show more

Keywords: Collision, contact threshold, differential equation, finite element analysis, vehicle safety

DOI: 10.3233/JIFS-233628

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 10019-10034, 2024

Authors: Nagamani, T. | Logeswari, S.

Article Type: Research Article

Abstract: A common cardiovascular illness with high fatality rates is coronary artery disease (CAD). Researchers have been exploring alternative methods to diagnose and assess the severity of CAD that are less invasive, cost-effective, and utilize noninvasive clinical data. Machine learning algorithms have shown promising and potential results. Accordingly, this study focuses on assisting medical practitioners with CAD detection by using a hybrid classification system combining XGBoost and Adam optimization. The primary approach incorporates One-Hot encoding to transform categorical attributes within the dataset, enhancing the precision of predictions. The secondary approach constitutes a hybrid classification model integrating XGBoost and employing Adam optimizations …for CAD detections. The efficacy of the recommended method is assessed using the cleveland, Hungarian, and Statlog heart-disease data sets. The proposed system and the standard Grid and Random Search classifiers are compared. The experimental outcomes indicate that the suggested model achieves a notable prediction accuracy of 94.19%. This represents an improvement of 7 to 8% over the existing grid search algorithm and 2 to 3% improvement over the random search algorithm for the above all datasets. Hence, the proposed system can be a valuable tool for identifying CAD patients, offering enhanced prediction accuracy. Show more

Keywords: Adam optimization, coronary artery disease, grid search, one hot encoding, random search, XGBoost

DOI: 10.3233/JIFS-233804

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 10035-10044, 2024

Authors: Pan, Hongyan

Article Type: Research Article

Abstract: In addition to providing learners with a large amount of teaching resources, online teaching platforms can also provide learning resources and channels such as video courseware, Q&A tutoring groups, and forums. However, currently, there are still shortcomings in depth and dimensionality in mining student learning behavior data on the platform. In view of this situation, based on the learning interaction behavior, this study established the difficulty similarity model of knowledge points, and used spectral clustering to classify their difficulty. In addition, the study intended to use the maximum frequent subgraph under the Gspan framework to characterize learners’ implicit learning patterns. …The outcomes expressed that the algorithm put forward in the study achieved the highest accuracy index of 98.8%, which was 1.4%, 4.0%, and 8.6% higher than Apriori-based graph mining algorithms, K-means, and frequent subgraph discovery algorithms. In terms of F1 index, the convergence value of the algorithm proposed in the study was 95.5%, which was about 2.5% higher than the last three algorithms. In addition, learners of all three cognitive levels had the highest maximum number of frequent subgraphs with sizes above 100 when the minSup value was 60%. And when the number of clusters was 3, the clustering accuracy of the three learners was the highest. In similarity calculation, the calculation method used in the study was at the minimum in terms of root mean square error and absolute error average index, which were 0.048% and 0.01% respectively. This indicated that the model proposed by the research had better classification effect on the difficulty of knowledge points for learners of different cognitive levels, and had certain application potential. Show more

Keywords: Similarity, knowledge points, clustering, multidimensional, Gspan, accuracy

DOI: 10.3233/JIFS-234274

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 10045-10058, 2024