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

Authors: Li, Zhaowen | Liao, Shimin | Qu, Liangdong | Song, Yan

Article Type: Research Article

Abstract: Attribute selection in an information system (IS) is an important issue when dealing with a large amount of data. An IS with incomplete interval-value data is called an incomplete interval-valued information system (IIVIS). This paper proposes attribute selection approaches for an IIVIS. Firstly, the similarity degree between two information values of a given attribute in an IIVIS is proposed. Then, the tolerance relation on the object set with respect to a given attribute subset is obtained. Next, θ -reduction in an IIVIS is studied. What is more, connections between the proposed reduction and information entropy are revealed. Lastly, three reduction …algorithms base on θ -discernibility matrix, θ -information entropy and θ -significance in an IIVIS are given. Show more

Keywords: Rough set theory, IIVIS, similarity degree, θ-reduction, θ-discernibility matrix, θ-information entropy, θ-significance, algorithm

DOI: 10.3233/JIFS-200394

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8775-8792, 2021

Authors: Li, Dong | Sun, Xin | Gao, Furong | Liu, Shulin

Article Type: Research Article

Abstract: Compared with the traditional negative selection algorithms produce detectors randomly in whole state space, the boundary-fixed negative selection algorithm (FB-NSA) non-randomly produces a layer of detectors closely surrounding the self space. However, the false alarm rate of FB-NSA is higher than many anomaly detection methods. Its detection rate is very low when normal data close to the boundary of state space. This paper proposed an improved FB-NSA (IFB-NSA) to solve these problems. IFB-NSA enlarges the state space and adds auxiliary detectors in appropriate places to improve the detection rate, and uses variable-sized training samples to reduce the false alarm rate. …We present experiments on synthetic datasets and the UCI Iris dataset to demonstrate the effectiveness of this approach. The results show that IFB-NSA outperforms FB-NSA and the other anomaly detection methods in most of the cases. Show more

Keywords: Negative selection algorithm, anomaly detection, artificial immune algorithms, machine learning

DOI: 10.3233/JIFS-200405

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8793-8806, 2021

Authors: Fan, Yun | Fang, Zhigeng | Liu, Sifeng | Liu, Jun

Article Type: Research Article

Abstract: The construction of more nursing homes has become one of the most needed pension services in China, and the issue of site selection is one of the most important steps in their construction. The problem of site selection for nursing homes is a complex system engineering problem that involves not only economic interests but also social interests. Due to the limitations of human thinking in the evaluation process, the evaluation value of a nursing home site might be an interval grey number. Moreover, the evaluation indicator system for nursing home locations is a two-layer system that has been neglected in …the literature. Therefore, the fuzzy analytical hierarchy process is extended to a new grey approach, i.e., the grey analytic hierarchy process, which can solve the evaluation problems for a two-layer indicator system under an interval grey environment. By constructing a three-point interval grey number, grey evaluation criteria are given to obtain a judgment matrix for interval grey numbers. Definitions of the initial weights, nongreyness weights and integrated weights are proposed to find the best evaluation object. Finally, the effectiveness of the method proposed by this paper is verified by comparative analyses of other grey methods. Show more

Keywords: Nursing home site, site selection, grey analytic hierarchy process, fuzzy analytic hierarchy process, interval grey number

DOI: 10.3233/JIFS-200480

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8807-8818, 2021

Authors: Meniz, Busra | Bas, Sema Akin | Ozkok, Beyza Ahlatcioglu | Tiryaki, Fatma

Article Type: Research Article

Abstract: Decision making (DM) is an important process encountered in every moment of life. Since it is difficult to interpret life depending on a single criterion, Multi-Criteria Decision Making (MCDM) enables to make decisions easier by creating appropriate choice in situations of uncertainty, complexity, and conflicting objectives. Therefore, we have studied the Analytic Hierarchy Process (AHP) which is one of the MCDM methods based on binary comparison logic. When uncertainties concerning the nature of life are considered, the solution procedure of AHP has been addressed by using Interval Type-2 Fuzzy Numbers (IT2FN)s to obtain more realistic results. The usability of AHP …with IT2FN is increased by amplifying hierarchy with sub-levels. Since sub-criterion may also need to be evaluated on sub-criteria in some cases of real multi-criteria problems, it is explicitly essential that each of sub-sub-criterion is included in the hierarchy at the own level in the real sense. In this paper, a new multilevel type-2 fuzzy AHP method is expanded by adding sub-criteria to the Interval Type-2 Fuzzy AHP (IT2FAHP) method developed by Kahraman et al. [C. Kahraman, B. Öztayşi, İ. Sarı and B. Turanoğlu, Fuzzy analytic hierarchy process with interval type-2 fuzzy sets, Knowledge-Based Systems 59 (2014), 48–57.]. Thanks to the extended method, another aim is to ensure that even complex situations that have multiple levels can be solved simply. Also, the proposed method is illustrated with a portfolio selection problem. Thus, the AHP method with type-2 fuzzy sets is carried out to the portfolio selection problem, which is in the scope of finance theory, for the first time in the literature. Show more

Keywords: Interval type-2 fuzzy numbers, multilevel AHP, multi-criteria decision making, portfolio selection

DOI: 10.3233/JIFS-200512

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8819-8829, 2021

Authors: Liu, Wanzheng | Xu, Ying | Shao, Meng | Yue, Guodong | An, Dong

Article Type: Research Article

Abstract: In this paper, a Stewart’s positive solution optimization model is proposed, for obtaining the complex solution to a Stewart’s forward kinematics problem, considering the existence of multiple solutions. The model converts the positive kinematics problem into an optimization problem, in which the value of the objective function is used to represent the precision of Stewart’s positive solution. A self-aggregating moth–flame optimization algorithm (SMFO) is used to improve the accuracy of Stewart’s forward kinematics solution. Two features were added to the conventional MFO algorithm to obtain a more stable balance between global and local explorations. First, Gaussian distribution was used for …the flame population to select suitable individuals for Levy Flight operation, increase the diversity of the population, and enhance the algorithm’s ability to jump out of a local optimum. Second, in the middle and late iterations, the positions of the flames were periodically adjusted using the light intensity-attraction characteristic (LIAC) to strengthen the connection between individual flames and enhance the local exploration ability of the algorithm. The proposed SMFO algorithm is compared with three classic meta-heuristic algorithms for eight benchmark functions. Experimental results indicate that the SMFO algorithm is significantly better than the other three algorithms in terms of solution quality and convergence rate. To verify the effectiveness of the SMFO algorithm in solving the Stewart positive kinematics optimization model, values of eight sets of conventional position and posture parameters as well as limiting position and posture parameters were randomly obtained, and values of 16 sets of position and posture parameters were obtained using four algorithms. The results indicate that the SMFO algorithm can improve the accuracy of the forward kinematics solution to 4.05E-09 mm. Show more

Keywords: Stewart platform, positive solution optimization model, light intensity-attraction characteristics, levy flight

DOI: 10.3233/JIFS-200656

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8831-8846, 2021

Authors: Elakkiya, R.

Article Type: Research Article

Abstract: Epilepsy is found to be the fourth most common chronic neurological disorder that tends to abnormal and unpredictable brain activity and seizure states. According to statistics, 70% of the epilepsy patients can be cured if identified and treated with anti-epileptic drugs or shock stimulations. Only about 7% to 8% need to be operated. Electroencephalogram (EEG) is a cheap and effective way to record the prolonged activities of the brain through electrical impulses between neural cells. Seizure is difficult to detect in neonates as the signal involves a lot of disturbances and the existing high accuracy system for adults can’t be …used for neonates. In an attempt to build an impregnable system to detect seizure in early stages, EEG signals of neonates procured from Neonatal Intensive Care Unit (NICU) at the Helsinki University Hospital. These signals were processed and fed into three different robust algorithms –Support Vector Machine (SVM), Artificial Neural Network (ANN) and 1-Dimensional Convolutional Neural Network (1D-CNN). The experimental results were compared and the proposed CNN model with 95.99% accuracy outperforms all the state-of-art models for automated Epileptic Seizure prediction in Neonates. Deep CNN has been a powerful tool in extracting robust features from EEG signals. This generalized system can be used by medical experts for detecting Seizure in neonates with better accuracy and reliability. Show more

Keywords: Neonatal Epileptic Seizure, neurological disorder, neonates, EEG, ANN, 1D-CNN, deep learning, Helsinki dataset, computer vision

DOI: 10.3233/JIFS-200800

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8847-8855, 2021

Authors: Li, Xi | Suo, Chunfeng | Li, Yongming

Article Type: Research Article

Abstract: An essential topic of interval-valued intuitionistic fuzzy sets(IVIFSs) is distance measures. In this paper, we introduce a new kind of distance measures on IVIFSs. The novelty of our method lies in that we consider the width of intervals so that the uncertainty of outputs is strongly associated with the uncertainty of inputs. In addition, better than the distance measures given by predecessors, we define a new quaternary function on IVIFSs to construct the above-mentioned distance measures, which called interval-valued intuitionistic fuzzy dissimilarity function. Two specific methods for building the quaternary functions are proposed. Moreover, we also analyzed the degradation of …the distance measures in this paper, and show that our measures can perfectly cover the measures on a simpler set. Finally, we provide illustrative examples in pattern recognition and medical diagnosis problems to confirm the effectiveness and advantages of the proposed distance measures. Show more

Keywords: Interval-valued intuitionistic fuzzy set, interval-valued distance measure, interval-valued intuitionistic fuzzy dissimilarity function, pattern recognition, medical diagnosis

DOI: 10.3233/JIFS-200889

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8857-8869, 2021

Authors: Wei, Guangcun | Rong, Wansheng | Liang, Yongquan | Xiao, Xinguang | Liu, Xiang

Article Type: Research Article

Abstract: Aiming at the problem that the traditional OCR processing method ignores the inherent connection between the text detection task and the text recognition task, This paper propose a novel end-to-end text spotting framework. The framework includes three parts: shared convolutional feature network, text detector and text recognizer. By sharing convolutional feature network, the text detection network and the text recognition network can be jointly optimized at the same time. On the one hand, it can reduce the computational burden; on the other hand, it can effectively use the inherent connection between text detection and text recognition. This model add the …TCM (Text Context Module) on the basis of Mask RCNN, which can effectively solve the negative sample problem in text detection tasks. This paper propose a text recognition model based on the SAM-BiLSTM (spatial attention mechanism with BiLSTM), which can more effectively extract the semantic information between characters. This model significantly surpasses state-of-the-art methods on a number of text detection and text spotting benchmarks, including ICDAR 2015, Total-Text. Show more

Keywords: Scene text spotting, End-to-end, Joint optimization, TCM, SAM-BiLSTM

DOI: 10.3233/JIFS-200903

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8871-8881, 2021

Authors: Guo, Feiyan | Tang, Bing | Zhang, Jiaming

Article Type: Research Article

Abstract: The rapid development of the Internet of Things and 5G networks have generated a large amount of data. By offloading computing tasks from mobile devices to edge servers with sufficient computing resources, network congestion and data transmission delays can be effectively reduced. The placement of edge server is the core of task offloading and is a multi-objective optimization problem with multiple resource constraints. Efficient placement approach can effectively meet the needs of mobile users to access services with low latency and high bandwidth. To this end, an optimization model of edge server placement has been established in this paper through …minimizing both communication delay and load difference as the optimization goal. Then, an E dge S erver placement based on meta-H euristic alG orithM (ESH-GM) has been proposed to achieve multi-objective optimization. Firstly, the K-means algorithm is combined with the ant colony algorithm, and the pheromone feedback mechanism is introduced into the placement of edge servers by emulating the mechanism of ant colony sharing pheromone in the foraging process, and the ant colony algorithm is improved by setting the taboo table to improve the convergence speed of the algorithm. Then, the improved heuristic algorithm is used to solve the optimal placement of edge servers. Experimental results using Shanghai Telecom’s real datasets show that the proposed ESH-GM achieves an optimal balance between low latency and load balancing, while guaranteeing quality of service, which outperforms several existing representative approaches. Show more

Keywords: Mobile edge computing, server placement, heuristic algorithm, performance optimization

DOI: 10.3233/JIFS-200933

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8883-8897, 2021

Authors: Kang, Keming | Tian, Shengwei | Yu, Long

Article Type: Research Article

Abstract: For deep learning’s insufficient learning ability of a small amount of data in the Chinese named entity recognition based on deep learning, this paper proposes a named entity recognition of local adverse drug reactions based on Adversarial Transfer Learning, and constructs a neural network model ASAIBC consisting of Adversarial Transfer Learning, Self-Attention, independently recurrent neural network (IndRNN), Bi-directional long short-term memory (BiLSTM) and conditional random field (CRF). However, of the task of Chinese named entity recognition (NER), there are only few open labeled data sets. Therefore, this article introduces Adversarial Transfer Learning network to fully utilize the boundary of Chinese …word segmentation tasks (CWS) and NER tasks for information sharing. Plus, the specific information in the CWS is also filtered. Combing with Self-Attention mechanism and IndRNN, this feature’s expression ability is enhanced, thus allowing the model to concern the important information of different entities from different levels. Along with better capture of the dependence relations of long sentences, the recognition ability of the model is further strengthened. As all the results gained from WeiBoNER and MSRA data sets by ASAIBC model are better than traditional algorithms, this paper conducts an experiment on the data set of Xinjiang local named entity recognition of adverse drug reactions (XJADRNER) based on manual labeling, with the accuracy, precision, recall and F-Score value being 98.97%, 91.01%, 90.21% and 90.57% respectively. These experimental results have shown that ASAIBC model can significantly improve the NER performance of local adverse drug reactions in Xinjiang. Show more

Keywords: Transfer learning, self-Attention mechanism, IndRNN, named entity recognition of adverse drug reactions, deep learning

DOI: 10.3233/JIFS-201017

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8899-8914, 2021