Authors: Chen, Aiguo | Qian, Pengjiang | Wang, Shitong | Jiang, Yizhang
Article Type: Research Article
Abstract: As one of feasible clustering techniques for large-scale data, incremental fuzzy clustering, which copes with data in chunks, has triggered more attentions in recent years. The existing methods, such as online fuzzy C -medoids (OFCMd) and history-based online fuzzy C -medoids (HOFCMd), employ only one medoid to represent each cluster in chunks. Due to the fact that the representativeness of the one-medoid modality is sometimes unsatisfactory, a novel large-scale fuzzy multiple-medoid clustering (LS-FMMdC) method is presented to strengthen the clustering effectiveness for large-scale data. The performance of the proposed method is verified by comparing LS-FMMdC with OFCMd and HOFCMd on …both synthetic and real-life large-scale data sets. Show more
Keywords: Fuzzy C-medoids, incremental clustering, data chunk, multiple medoids, large-scale data
DOI: 10.3233/JIFS-152647
Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 3, pp. 1833-1845, 2017
Authors: Jiang, Yizhang | Deng, Zhaohong | Choi, Kup-Sze | Qian, Pengjiang | Hu, Wenjun | Wang, Shitong
Article Type: Research Article
Abstract: Group probability classifier learning is an emerging and promising learning technique, especially in privacy-preserving data mining. It is used to train a classifier from a group probability dataset, where the class labels of each sample are unknown while the probabilities of each class in the given data groups of the whole dataset are available. The existing work is mainly based on the inverse calibration (IC) strategy to obtain the estimated labels for data in the group probability dataset and then make use of classical classification algorithms such as support vector machine (SVM) model to train the desired classifier. A critical …challenge of the exiting IC-based methods lies in the difficulty of designing an ideal IC function for label estimation and the methods are sensitive to the adopted IC function. In order to overcome this shortcoming, a novel probability transductive classifier that does not involve IC in the learning procedure is proposed, where the probability values are directly used as the output of the training data for the model training. Particularly, on the training data with the output being continuous real values, the existing classical regression model can be easily adopted to model the group probability classification problem. For a future testing data, the model output of the obtained group probability classification model can present the probability that the testing data belong to the positive class. With a given threshold, the final class label of the testing data can be obtained for the classification task. The experimental results on synthetic datasets and real UCI datasets show that the proposed method is more effective than the existing methods. Show more
Keywords: Privacy preserving, regression model, probability transductive, group probability, classification
DOI: 10.3233/IFS-151621
Citation: Journal of Intelligent & Fuzzy Systems, vol. 29, no. 2, pp. 917-925, 2015
Authors: Tao, Yuwen | Jiang, Yizhang | Xia, Kaijian | Xue, Jing | Zhou, Leyuan | Qian, Pengjiang
Article Type: Research Article
Abstract: The use of machine learning technology to recognize electrical signals of the brain is becoming increasingly popular. Compared with doctors’ manual judgment, machine learning methods are faster. However, only when its recognition accuracy reaches a high level can it be used in practice. Due to the difference in the data distributions of the training dataset and the test dataset and the lack of training samples, the classification accuracies of general machine learning algorithms are not satisfactory. In fact, among the many machine learning methods used to process epilepsy electroencephalogram (EEG) signals, most are black box methods; however, in medicine, methods …with explanatory power are needed. In response to these three challenges, this paper proposes a novel technique based on domain adaptation learning, semi-supervised learning and a fuzzy system. In detail, we use domain adaptation learning to reduce deviation from the data distribution, semi-supervised learning to compensate for the lack of training samples, and the Takagi-Sugen-Kang (TSK) fuzzy system model to improve interpretability. Our experimental results show that the performance of the new method is better than those of most advanced epilepsy classification methods. Show more
Keywords: EEG signal recognition, epilepsy classification, integrated learning mechanism, domain adaptation learning, semi-supervised learning, TSK fuzzy system
DOI: 10.3233/JIFS-201673
Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 3, pp. 4851-4866, 2021
Authors: Tao, Yuwen | Jiang, Yizhang | Dong, Xuan | Zhou, Leyuan | Ding, Yang | Qian, Pengjiang
Article Type: Research Article
Abstract: Epilepsy is a common brain disease, caused by abnormal discharge of human brain neurons, resulting in brain dysfunction syndrome. Although epilepsy does not have much impact on patients in the short term, but long-term frequent seizures can lead to physical and mental impact of patients. At present, the method used to detect epilepsy is to make a comprehensive judgment by EEG examination combined with clinical symptoms. With the application of AI technology, some advanced algorithms have been used to assist medical diagnosis. In this trend, we use extreme learning machine to observe and detect patients with epilepsy. ELM has the …characteristics of high efficiency and high precision, so it is often used in regression and classification problems. However, in the face of different data sets, ELM structure is not enough to achieve good performance. This is caused by the uneven distribution of data in different data sets. To solve this problem, we add the transfer learning module to the basic ELM structure. The purpose of adding transfer learning is to divide the disordered data in the domain space and construct a data set suitable for ELM learning. Specifically, the raw data are mapped to high-dimensional space by kernel method through domain adaptive method. Secondly, in high-dimensional space, the distance between different domains should be reduced appropriately. Finally, ELM method is used to analyze and predict the changed data set. In the whole algorithm process, due to the characteristics of ELM updating weight, only a certain amount of hidden nodes are needed, and the training process is very fast. At the same time, after adding the transfer learning function module, the accuracy of ELM is also satisfactory. In this paper, the epilepsy data of patients were used for comparative experiments. The experimental results show that the method can maintain high efficiency and satisfactory accuracy. Show more
Keywords: Extreme learning machine, domain adaptation, signal classification, Epileptic EEG
DOI: 10.3233/JIFS-212068
Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 3983-3992, 2022