The rapid development in data science and the increasing availability of building operational data have provided great opportunities for developing data-driven solutions for intelligent building energy management. Data preprocessing serves as the foundation for valid data analyses. It is an indispensable step in building operational data analysis considering the intrinsic complexity of building operations and deficiencies in data quality. Data preprocessing refers to a set of techniques for enhancing the quality of the raw data, such as outlier removal and missing value imputation. This article serves as a comprehensive review of data preprocessing techniques for analysing massive building operational data. A wide variety of data preprocessing techniques are summarised in terms of their applications in missing value imputation, outlier detection, data reduction, data scaling, data transformation, and data partitioning. In addition, three state-of-the-art data science techniques are proposed to tackle practical data challenges in the building field, i.e., data augmentation, transfer learning, and semi-supervised learning. In-depth discussions have been presented to describe the pros and cons of existing preprocessing methods, possible directions for future research and potential applications in smart building energy management. The research outcomes are helpful for the development of data-driven research in the building field.

No abstract

No abstract

No abstract

As a typical multi-objective optimization problem, parameter optimization of HEV power control strategy must deal with the conflict between objectives, as fuel consumption and emissions. Classical methods define the HEV parameter optimization as a single objective problem to minimize the fuel consumption. In this paper, the multi-objective genetic algorithm (MOGA) is generalized for parameter optimization of power control strategy of series hybrid electric vehicle. Using a single unified formulation, a number of design objectives can be simultaneously optimized through searching in the parameter space. Compared with two main strategies, as Thermostatic and singleobjective genetic algorithm (SOGA), the computation procedures of MOGA are discussed. Simulation results based on the model of series hybrid electric vehicle illustrate the optimization validity of MOGA.Index Terms-Multi-objective genetic algorithm, power control strategy, series hybrid electric vehicle, parameter optimization

No abstract

This paper presents a method for modeling hu-B. Related Work man abnormal gait using hidden Markov model under the framework of a shoe-integrated system. The intelligent systemIn the past decade, as more and more studies on human focuses on modeling the following patterns: normal gait, toe in gait are conducted, numerous systems for gait data acquiand toe out gait abnormalities. In the developed prototype, an sition and analysis are proposed, such as camera based, inertial measurement unit (IMU) consisting of three-dimensional floor-mounted, and in-shoe configuration systems. However, gyroscopes and accelerometers is employed to measure angular velocities and accelerations of human foot. Four force sensing among all theavailbl gssems, iof endeice i mst. resistors (FSRs) and one bend sensor are arranged on a insole utilzed due to the outstanding merit of extending the usable of each foot for force and flexion information acquisition. The location for human gait study. An in-shoe multisensory data proposed method is mainly based on Principal Component acquisition system was reported by Morley et al. in 2001 Analysis (PCA) for feature generation and hidden Markov[1]. In the system, except for pressure sensors, temperature model (HMM) for multi-pattern modeling. The "similarity and humidity sensors are located in a shoe to monitor distance measure" criterion is introduced to do model-tomodel evaluation. Experiment results demonstrate the proposed the corresponding information. However, the system mainly approach is robust and efficient in detecting abnormal gait focused on the hardware design and less discussion about patterns. Our goal is to provide a cost-effective system for data interpretation and analysis was introduced. Morris has detecting gait abnormalities in order to assist persons with developed a wireless sensor system for realtime data acquisiabnormal gaits in developing the normal walking pattern in tion which has the potential use in clinical gait analysis [2]. their daily life.ho hchath oealuen lnclgtaayss[] More introductions about prototype design were presented Index Terms-Shoe-integrated system, abnormal gait, hidden and the pattern recognition method was not mentioned in Markov model, similarity distance measure. detail. Besides, Pedar insole system (Novel, Munich) is a commercially available system which is widely used in clinic sites and laboratories due to its repeatability and accuracy [3].

No abstract