Journal of Intelligent & Fuzzy Systems - Volume 40, issue 5

Authors: Khudoyberdiev, Azimbek | Ullah, Israr | Kim, DoHyeun

Article Type: Research Article

Abstract: Remarkable resource management and energy efficiency improvements can be achieved in greenhouses using innovative technological advancements and modern agricultural methods. Deployment of Internet of Things (IoT) and optimization algorithms in greenhouse farming is highly desirable for real-time monitoring and controlling various parameters with optimal solutions. However, IoT based greenhouses require more energy as compared to traditional farming. This paper proposes an optimal greenhouse water supplement mechanism with efficient energy consumption based on IoT and optimization techniques. The first contribution of this study is to gather the actual water and soil moisture levels from the greenhouse and tank using IoT devices. …Secondly, the formulation and deployment of an objective function to compute the optimal water and soil moisture levels for greenhouse and tank based on user-desired settings, the system constraints and actual sensing values. We applied a rule-based expert system to activate water pumps with the required flow rate and operational duration to achieve efficient energy consumption. To prove the effectiveness of the proposed concept, embedded IoT devices and objective function for optimization are deployed as well as, a number of experiments are conducted to provide the optimal water and soil moisture levels in a real greenhouse and water tank environment. Show more

Keywords: Internet of Things (IoT), objective function, optimization, water tank, energy efficiency, rule-based expert systems

DOI: 10.3233/JIFS-200618

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10163-10182, 2021

Authors: Mortaji, Seyed Taha Hossein | Noori, Siamak | Bagherpour, Morteza

Article Type: Research Article

Abstract: Earned value management is well-known as the most efficient method of project monitoring and control providing relatively reliable information about the project performance. However, this method requires accurate estimates of the progress of project activities, which are always associated with uncertainties that, if ignored or not addressed well, lead to incorrect results. To address this issue, the application of multi-valued logic, in particular fuzzy logic, in earned value management has recently attracted a lot of attention both in practice and research. This paper introduces directed earned value management (DEVM) in which ordered fuzzy numbers are used to express the so-called …uncertainties as well as to capture more information about the trend of the project progress. To evaluate the performance of the proposed method, several numerical examples and a case study are presented. The results reveal that compared to the existing methods, DEVM has a lower computational complexity. Also, it doesn’t suffer from the overestimation effect and as a result, it has a higher ability to express project-specific dynamics. In sum, the proposed method allows project managers to make informed decisions that lead to taking preventive and corrective actions promptly and at a lower cost. Show more

Keywords: Earned value management, fuzzy earned value management, fuzzy performance indicators, ordered fuzzy numbers, directed earned value management

DOI: 10.3233/JIFS-201248

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10183-10196, 2021

Authors: Zhang, Haowen | Dong, Yabo | Xu, Duanqing

Article Type: Research Article

Abstract: Time series classification is a fundamental problem in the time series mining community. Recently, many sophisticated methods which can produce state-of-the-art classification accuracy on the UCR archive have been proposed. Unfortunately, most of them are parameter-laden methods and require fine-tune for different datasets. Besides, training these classifiers is very computationally demanding, which makes them difficult to use in many real-time applications and previously unseen datasets. In this paper, we propose a novel parameter-light algorithm, MDTW, to classify time series. MDTW has a few parameters which do not require any fine-tune and can be chosen arbitrarily because …the classification accuracy is largely insensitive to the parameters. MDTW has no training step; thus, it can be directly applied to unseen datasets. MDTW is based on a popular method, namely the nearest neighbor classifier with Dynamic Time Warping (NN-DTW). However, MDTW performs much faster than NN-DTW by representing time series in different resolutions and using filters-and-refine framework to find the nearest neighbor. The experimental results demonstrate that MDTW performs faster than the state-of-the-art, with small losses (<3%) in average classification accuracy. Besides, we embed a technique, prunedDTW, into the MDTW procedure to make MDTW even faster, and show by experiments that this combination can speed up the MDTW from one to five times. Show more

Keywords: Time series classification, Dynamic Time Warping, nearest neighbor, multilevel representations, filters-and-refine

DOI: 10.3233/JIFS-201281

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10197-10210, 2021

Authors: Xiao, Yanjun | Yu, Anqi | Qi, Hao | Jiang, Yunfeng | Zhou, Wei | Gao, Nan | Liu, Weiling

Article Type: Research Article

Abstract: In the industrial field, the lithium battery industry has a long history and a large market scale. Lithium battery electrode strip rolling mill belongs to the high-end production equipment in the lithium battery industry. However, due to its complex structure, the tension of lithium battery electrode mill is prone to large fluctuation. This will lead to the phenomenon of wrinkle and looseness, which will affect the quality of the electrode strip. At present, the tension control method of lithium battery electrode mill mostly adopts traditional Proportional-Integral-Differential(PID) control. Under this control mode, the production speed and precision of lithium battery electrode …mill need to be improved. In this paper, the fuzzy PID tension control method of lithium battery electrode mill based on genetic optimization is studied. Based on fuzzy theory and PID control method, a tension fuzzy PID model is established for experimental verification, and the initial parameters and fuzzy rules of fuzzy PID are optimized by Genetic Algorithm(GA). This method has better stability, can improve the precision of strip tension control, make the tension more stable when the rolling mill is running, and help to improve the quality of electrode strip production. Show more

Keywords: Fuzzy theory, genetic algorithm, lithium battery electrode mill, PID, tension

DOI: 10.3233/JIFS-201675

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10211-10234, 2021

Authors: Chen, Yan | song, Huan-sheng | yang, Yan-ni | wang, Gang-feng

Article Type: Research Article

Abstract: Mixture production equipment is widely employed in road construction, and the quality of the produced mixture is the essential factor to ensure the quality of road construction. To detect the quality of the real-time produced mixture and solve the shortcomings of laboratory detection lag, a new fault detection method in the mixture production process is proposed, which is based on wavelet packet decomposition (WPD) and support vector machine (SVM). The proposed scheme includes feature extraction, feature selection, SVM classification, and optimization algorithm. During feature extraction, wavelet basis function is utilized to 4-layer decompose the aggregate and asphalt data mixed in …real-time. The energy value calculated by wavelet packet coefficient is the extracted feature. During feature selection, a method combining the chi-square test and wrapper (CSW) is conducted to select the optimal feature subset from WPD features. Eventually, by adopting the optimal feature subset, SVM has been developed to classify various faults. Its parameters are optimized by differential evolution (DE) algorithm. In the test stage, multiple faults of different specifications of aggregates and asphalt are detected in the mixture production process. The results demonstrate that (1) accuracy produced by the CSW method with WPD features is 4.33% higher than the PCA method with statistical features; (2) SVM classification method optimized by DE algorithm brings an increase in recognition accuracy of identifying different types of mixture production faults produced by different equipment. Compared to other available methods, the proposed algorithm has a very outstanding detection performance. Show more

Keywords: Mixture production process, fault detection, wavelet packet decomposition (WPD) features, support vector machine (SVM), differential evolution (DE)

DOI: 10.3233/JIFS-201803

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10235-10249, 2021

Authors: Zhang, Zhenghang | Jia, Jinlu | Wan, Yalin | Zhou, Yang | Kong, Yuting | Qian, Yurong | Long, Jun

Article Type: Research Article

Abstract: The TransR model solves the problem that TransE and TransH models are not sufficient for modeling in public spaces, and is considered a highly potential knowledge representation model. However, TransR still adopts the translation principles based on the TransE model, and the constraints are too strict, which makes the model’s ability to distinguish between very similar entities low. Therefore, we propose a representation learning model TransR* based on flexible translation and relational matrix projection. Firstly, we separate entities and relationships in different vector spaces; secondly, we combine our flexible translation strategy to make translation strategies more flexible. During model training, …the quality of generating negative triples is improved by replacing semantically similar entities, and the prior probability of the relationship is used to distinguish the relationship of similar coding. Finally, we conducted link prediction experiments on the public data sets FB15K and WN18, and conducted triple classification experiments on the WN11, FB13, and FB15K data sets to analyze and verify the effectiveness of the proposed model. The evaluation results show that our method has a better improvement effect than TransR on Mean Rank, Hits@10 and ACC indicators. Show more

Keywords: Knowledge representation, flexible translation, relation matrix projection, link prediction, triple classification

DOI: 10.3233/JIFS-202177

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10251-10259, 2021

Authors: Hu, Miao | Peng, Junjie | Zhang, Wenqiang | Hu, Jingxiang | Qi, Lizhe | Zhang, Huanxiang

Article Type: Research Article

Abstract: Intent recognition is one of the most essential foundations as well as a very challenging task for language understanding, especially for spoken language. As spoken text is short, and lack of full context. Moreover, it may mix multi-language forms. These non-standard spoken expressions further lead to the shortage of text information. In consideration that sparse text information seriously affects the effect of intention understanding, a multi-feature fusion-based intent recognition model for the bilingual phenomenon mixed with Chinese and English is proposed. Combining word2vec and multilingual wordNets with the same synset_id (synonym set id), the model can mask the differences between …different languages. Meanwhile, it can enrich the information representation of the spoken text by fusing the word intention features with the context-dependent features represented by transformer as well as the word frequency features. To verify the correctness and effectiveness of the model, extensive experiments were conducted on a real online logistics customer service platform and SMP2018-ECDT dataset. The results show that our model is superior to other models. And it improves the accuracy of intent recognition in logistics data by 20% compared with that of transformer. Show more

Keywords: Intent recognition, word intent feature, context dependency, wordNet

DOI: 10.3233/JIFS-202365

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10261-10272, 2021

Authors: Mirsadeghpour Zoghi, S.M. | Sanei, M. | Tohidi, G. | Banihashemi, Sh. | Modarresi, N.

Article Type: Research Article

Abstract: According to modern finance theory and increasing need for efficient investments, we evaluate the portfolio performance based on the data envelopment analysis method. By the fact that stock market’s return distributions usually exhibit skewness, kurtosis and heavy-tails, we consider some appropriate underlying distributions that affect the input and output of the model. In this regard, the multivariate skewed t and the multivariate generalized hyperbolic as the heavy-tailed distributions of Normal mean-variance mixture are applied. The models are inspired by the Range Directional Measure (RDM) model to deal with negative values. The value-at-risk (VaR) and conditional VaR (CVaR) as risk …measures are used in these optimization problems. We estimate the parameters of such distributions by Expectation Maximization algorithm. Then we present an empirical investigation to measure the relative efficiency of two sets of seven groups of companies from different industries of Iran stock exchange market. By comparing the results of introduced models with previous RDM approach, we show that how well the distribution of assets affect the performance evaluation. Show more

Keywords: Data envelopment analysis, normal mean-variance mixture distributions, portfolio optimization, VaR, CVaR

DOI: 10.3233/JIFS-202332

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10273-10283, 2021

Authors: Li, Xin | Li, Xiaoli | Wang, Kang

Article Type: Research Article

Abstract: In the past two decades, multi-objective evolutionary algorithms (MOEAs) have achieved great success in solving two or three multi-objective optimization problems. As pointed out in some recent studies, however, MOEAs face many difficulties when dealing with many-objective optimization problems(MaOPs) on account of the loss of the selection pressure of the non-dominant candidate solutions toward the Pareto front and the ineffective design of the diversity maintenance mechanism. This paper proposes a many-objective evolutionary algorithm based on vector guidance. In this algorithm, the value of vector angle distance scaling(VADS) is applied to balance convergence and diversity in environmental selection. In addition, tournament …selection based on the aggregate fitness value of VADS is applied to generate a high quality offspring population. Besides, we adopt an adaptive strategy to adjust the reference vector dynamically according to the scales of the objective functions. Finally, the performance of the proposed algorithm is compared with five state-of-the-art many-objective evolutionary algorithms on 52 instances of 13 MaOPs with diverse characteristics. Experimental results show that the proposed algorithm performs competitively when dealing many-objective with different types of Pareto front. Show more

Keywords: Vector angle distance scaling, evolutionary algorithm, many-objective optimization problem

DOI: 10.3233/JIFS-202724

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10285-10306, 2021

Authors: Gan, Weichao | Ma, Zhengming | Liu, Shuyu

Article Type: Research Article

Abstract: Tensor data are becoming more and more common in machine learning. Compared with vector data, the curse of dimensionality of tensor data is more serious. The motivation of this paper is to combine Hilbert-Schmidt Independence Criterion (HSIC) and tensor algebra to create a new dimensionality reduction algorithm for tensor data. There are three contributions in this paper. (1) An HSIC-based algorithm is proposed in which the dimension-reduced tensor is determined by maximizing HSIC between the dimension-reduced and high-dimensional tensors. (2) A tensor algebra-based algorithm is proposed, in which the high-dimensional tensor are projected onto a subspace and the projection coordinate …is set to be the dimension-reduced tensor. The subspace is determined by minimizing the distance between the high-dimensional tensor data and their projection in the subspace. (3) By combining the above two algorithms, a new dimensionality reduction algorithm, called PDMHSIC, is proposed, in which the dimensionality reduction must satisfy two criteria at the same time: HSIC maximization and subspace projection distance minimization. The proposed algorithm is a new attempt to combine HSIC with other algorithms to create new algorithms and has achieved better experimental results on 8 commonly-used datasets than the other 7 well-known algorithms. Show more

Keywords: Dimensionality reduction, tensor mode product, hilbert-schmidt independence criterion, reproducing kernel hilbert space

DOI: 10.3233/JIFS-202582

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10307-10322, 2021