Multi-task Fuzzy Clustering–Based Multi-task TSK Fuzzy System for Text Sentiment Classification

Text sentiment classification is an important technology for natural language processing. A fuzzy system is a strong tool for processing imprecise or ambiguous data, and it can be used for text sentiment analysis. This article proposes a new formulation of a multi-task Takagi-Sugeno-Kang fuzzy system (TSK FS) modeling, which can be used for text sentiment image classification. Using a novel multi-task fuzzy c-means clustering algorithm, the common (public) information among all tasks and the individual (private) information for each task are extracted. The information about clustering, for example, cluster centers, can be used to learn the antecedent parameters of multi-task TSK fuzzy systems. With the common and individual antecedent parameters obtained, a corresponding multi-task learning mechanism for learning consequent parameters is devised. Accordingly, a multi-task fuzzy clustering–based multi-task TSK fuzzy system (MTFCM-MT-TSK-FS) is proposed. When the proposed model is built, the information conveyed by the fuzzy rules formed is two-fold, including (1) common fuzzy rules representing the inter-task correlation information and (2) individual fuzzy rules depicting the independent information of each task. The experimental results on several text sentiment datasets demonstrate the validity of the proposed model.

Fuzzy Cluster Analysis and Prediction of Psychiatric Health Data Based on BPNN

PMH (psychiatry/mental health) is affected by many factors, among which there are numerous connections, so the prediction of PMH is a nonlinear problem. In this paper, BPNN (Back Propagation Neural Network) is applied to fuzzy clustering analysis and prediction of PMH data, and the rules and characteristics of PMH and behavioral characteristics of people with mental disorders are analyzed, and various internal relations among psychological test data are mined, thus providing scientific basis for establishing and perfecting early prevention and intervention of mental disorders in colleges and universities. Artificial neural network is a mathematical model of information processing, which is composed of synapses similar to the structure of brain neurons. The fuzzy clustering analysis and data prediction ability of optimized PMH data are obviously improved. Applying BPNN to the fuzzy clustering analysis and prediction of PMH data, analyzing the rules and characteristics of PMH and the behavioral characteristics of patients with mental disorders, can explore various internal relations among psychological test data, and provide scientific basis for establishing early prevention and intervention of mental disorders.

Research on Fast Face Retrieval Optimization Algorithm Based on Fuzzy Clustering

Aiming at the problem of long retrieval time for massive face image databases under a given threshold, a fast retrieval algorithm for massive face images based on fuzzy clustering is proposed. The algorithm builds a deep convolutional neural network model. The model can be used to extract features from face photos to obtain a high-dimensional vector to represent the high-level semantic features of face photos. On this basis, the fuzzy clustering algorithm is used to perform fuzzy clustering on the feature vectors of the face database to construct a retrieval pedigree map. When the threshold is passed in for database retrieval of the target face photos, the pedigree map can be quickly retrieved. Experiments on the LFW face dataset and self-collected face dataset show that the model is better than the commonly used K-means model in face recognition accuracy, clustering effect, and retrieval speed and has certain commercial value.

FCERP: A Novel WSNs Fuzzy Clustering and Energy Efficient Routing Protocol

Wireless sensor networks (WSNs) are set of sensor nodes to monitor and detect transmitted data to the sink. WSNs face significant challenges in terms of node energy availability, which may impact network sustainability. As a result, developing protocols and algorithms that make the best use of limited resources, particularly energy resources, is critical issues for designing WSNs. Routing algorithms, for example, are unique algorithms as they have a direct and effective relationship with lifetime of network and energy. The available routing protocols employ single-hop data transmission to the sink and clustering per round. In this paper, a Fuzzy Clustering and Energy Efficient Routing Protocol (FCERP) that lower the WSNs energy consuming and increase the lifetime of network is proposed. FCERP introduces a new cluster-based fuzzy routing protocol capable of utilizing clustering and multiple hop routing features concurrently using a threshold limit. A novel aspect of this research is that it avoids clustering per round while considering using fixed threshold and adapts multi-hop routing by predicting the best intermediary node for clustering and the sink. Some Fuzzy factors such as residual energy, neighbors amount, and distance to sink considered when deciding which intermediary node to use.