Search

The extreme learning machine (ELM) is famous for its single hidden-layer feed-forward neural network which results in much faster learning speed comparing with traditional machine learning techniques. Moreover, extensions of ELM achieve stable classification performances for imbalanced data. In this paper, we introduce a hybrid method combining the extended Kalman filter (EKF) with cost-sensitive dissimilar ELM (CS-D-ELM). The raw data are preprocessed by EKF to produce inputs for the CS-D-ELM classifier. Experimental results show that the proposed method is more suitable for real-time fault diagnosis of air handling units than traditional approaches. [ABSTRACT FROM AUTHOR]

App usage is now a ubiquitous phenomenon, but little is known about what types of psychological needs are met by which apps. We proposed a method to label automatically mobile apps in terms of whether and to what extent they can satisfy users’ particular psychological needs. First, using the grounded theory approach, we conducted semi-structured in-depth interviews to identify types of needs associated with app usage. Substantive and theoretical coding of the data from the interviews as well as data from samples of app reviews yielded eight types of psychological needs app users had: utilitarian, low-cost, security, health, hedonic, social, cognitive, and self-actualization needs. Second, using the needs corpus (words and phrases) generated above, a classifier was trained using latent Dirichlet allocation (LDA) and support vector machine (SVM) algorithms to filter reviews in terms of whether they included needs-related comments. The classifier showed good performance. Finally, Labeled-LDA was used to automatically provide each review with multiple labels of the types of needs mentioned and the apps were analyzed for the different types of needs they satisfied. [ABSTRACT FROM AUTHOR]

Automatic, accurate and online fault detection of heating ventilation air conditioning (HVAC) subsystems, such as chillers, is highly demanded in building management system (BMS) to prevent energy waste and high maintenance cost. However, most fault detection techniques require rich faulty training data which is usually unavailable. In this study, a novel hybrid method is proposed to detect faults for chiller subsystems without any faulty training data available, i.e. by training the normal data only. A hybrid feature selection algorithm is applied to the chiller dataset collected by ASHRAE project 1043-RP to select the most significant feature variables. An online classification framework is introduced by combining an Extended Kalman Filter (EKF) model and a recursive one-class support vector machine (ROSVM). Experiment results show that the proposing algorithm detects typical chiller faults with high accuracy rates and requires less feature variables compared to existing works. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a LSSVR-based time series method (LTSM) to predict dynamic lateral deformation of retaining structure and ground surface settlement in deep foundation pit engineering. After reconstructing phase space, time-varying lateral displacement of each observation point on retaining structure can be predicted using its historic unary time series data. And then, the ground settlement nearby the deep foundation pit can be predicted using all the observed values of lateral deformation which were collected at the same time from different depths on the retaining structure. The experimental results show that LTSM achieved a high accuracy when predicting the lateral deformation and ground settlement. [Copyright &y& Elsevier]

Fault detection and diagnosis (FDD) plays an essential role of maintaining large-scale heating ventilation air conditioning (HVAC) systems for industrial usage. The process of selecting important features is a crucial step for FDD methods of HVAC components, such as chillers. A suitable feature selection method selects the minimum number of features to save the number of installing sensors, and simultaneously maximizes the FDD accuracy. According to the surveyed related works, it is found that most existing works only focus on maximizing the classification accuracy, and miss two important points. First, the misclassification costs of false positive and false negative are different for chiller FDD. Second, the selected feature subsets must be sequential for real-world applications. In this study, a cost-sensitive and sequential feature selection algorithm for chiller FDD is proposed to select the most important features using a back-tracing sequential forward feature selection (BT-SFS) algorithm. The ASHRAE dataset collected by project number 1043-RP is utilized. Support vector machine (SVM), which is proved to be one of the most effective FDD classification method for chillers in existing works, is employed for accuracy measurement. This work fills in the gap between theoretical HVAC FDD methods and real-world HVAC FDD applications. [ABSTRACT FROM AUTHOR]