Search results

The purpose of this paper is to target on designing a short-term load prediction framework that can accurately predict the cooling load of office buildings.

A feature selection scheme and stacking ensemble model to fulfill cooling load prediction task was proposed. Firstly, the abnormal data were identified by the data density estimation algorithm. Secondly, the crucial input features were clarified from three aspects (i.e. historical load information, time information and meteorological information). Thirdly, the stacking ensemble model combined long short-term memory network and light gradient boosting machine was utilized to predict the cooling load. Finally, the proposed framework performances by predicting cooling load of office buildings were verified with indicators.

The identified input features can improve the prediction performance. The prediction accuracy of the proposed model is preferable to the existing ones. The stacking ensemble model is robust to weather forecasting errors.

The stacking ensemble model was used to fulfill cooling load prediction task which can overcome the shortcomings of deep learning models. The input features of the model, which are less focused on in most studies, are taken as an important step in this paper.

Uses data on 1,550 nonlethal assaults recorded by Baltimore County Police Department. Examines factors that are associated with the likelihood of officer injury after an assault. Notes that factors affecting the probability of assault do not necessarily correspond with the factors that affect the likelihood of injury. Analyzes a broader spectrum of contributory factors than those addressed by other research. Finds inter alia that greater officer proficiency in unarmed defensive tactics may reduce their assault‐related injuries, since most incidents do not involve arms; that in‐service training should be biased toward less experienced officers who are at greater risk; that officer height is a significant variable; that many officers suffer multiple attacks; that domestic disturbances do not rank higher than other dangers, but that this may reflect the possibility that officers anticipate potential violence and take better precautions before attending the scene.

The emergence of smart wearables using clothing as a technology platform is a significant milestone with considerable implications for industrial convergence, creating new value for fashion. This paper aimed to present a premeditated prototype to integrate a human activity recognition (HAR) system into outdoor clothing.

For the development of wearable HAR (WHAR) clothing, this paper explored three subject areas: fashion design related to the structural feature of the clothing platform, electronics related to wearable circuits and modules design and graphic user interface design related to smartphone application development.

For WHAR functions in outdoor terrains, the coexistence of accelerometer–gyroscope sensing and distance-sensing could be practical to surpass the technological limitation of activity and posture recognition with gyro sensors highly depending on the changes of acceleration and angles.

Through the vital sign check and physical activity–change recognition function, this study's WHAR system allows users to check their health by themselves and avoid overwork. A quick rescue is possible manually and automatically in a dangerous situation by notifying others. Thus, it can help protect users' health and safety (life).

This study designed the modularization of HAR functions generally installed in indoor medical spaces. Through the approach, smart clothing–embracing WHAR systems optimized for health and safety care for outdoor environments was pursued to diversify expensive roles of clothing for technological applications.

Chinese housing market has been growing fast during the past decade, and price-related forecasting has turned to be an important issue to various market participants, including the people, investors and policy makers. Here, the authors approach this issue by researching neural networks for rent index forecasting from 10 major cities for March 2012 to May 2020. The authors aim at building simple and accurate neural networks to contribute to pure technical forecasting of the Chinese rental housing market.

To facilitate the analysis, the authors examine different model settings over the algorithm, delay, hidden neuron and data spitting ratio.

The authors reach a rather simple neural network with six delays and two hidden neurons, which leads to stable performance of 1.4% average relative root mean square error across the ten cities for the training, validation and testing phases.

The results might be used on a standalone basis or combined with fundamental forecasting to form perspectives of rent price trends and conduct policy analysis.

The purpose of this paper is to develop a flexible design-oriented development cost method for commercial aviation aircraft based on small sample and poor information.

To predict the development cost of commercial aviation aircraft accurately, the methodology is based on the collected cost data and actual technical, and then the cost prediction relationships derived from an exhaustive statistical and filtered from regression analysis are incorporated. A series of regression equations with high regression coefficient are yielded after the cost driving factors of the development cost are fixed. Next, several sets of equations with high regression coefficient are selected for final integration. It is a flexible method that can be used efficiently to predict the cost of commercial aviation aircraft.

The development of commercial aviation aircraft has relatively a late start and no cost prediction model has been suitable for small sample, the proposed method is expected and is rather desirable.

By comparing the approach with the ordinary regression model and back propagation (BP) neural network, the scheme in this work is more efficient and convenient.

The results obtained in this paper show that the proposed method not only has a certain degree of versatility, but also can provide a preliminary prediction of the development cost of commercial aviation aircraft.

This paper aims to propose and verify an improved cascade active disturbance rejection control (ADRC) scheme based on output redefinition for hypersonic vehicles (HSVs) with nonminimum phase characteristic and model uncertainties.

To handle the nonminimum phase characteristic, a tuning factor stabilizing internal dynamics is introduced to redefine the system output states; its effective range is determined by analyzing Byrnes–Isidori normalized form of the redefined system. The extended state observers (ESOs) are used to estimate the uncertainties, which include matched and mismatched items in the system. The controller compensates observations in real time and appends integral terms to improve robustness against the estimation errors of ESOs.

Theoretical and simulation results show that the stability of internal dynamics is guaranteed by the tuning factor and the tracking errors of external commands are globally asymptotically stable.

The control scheme in this paper is expected to generate a reliable way for dealing with nonminimum phase characteristic and model uncertainties of HSVs.

In the framework of ADRC, a concise form of redefined outputs is proposed, in which the tuning factor performs a decisive role in stabilizing the internal dynamics of HSVs. By introducing an integral term into the cascade ADRC scheme, the compensation accuracy of matched and mismatched disturbances is improved.

This meshless collocation method is applicable not only to the Helmholtz equation with Dirichlet boundary condition but also mixed boundary conditions. It can calculate not only the high wavenumber problems, but also the variable wave number problems.

In this paper, the authors developed a meshless collocation method by using barycentric Lagrange interpolation basis function based on the Chebyshev nodes to deduce the scheme for solving the three-dimensional Helmholtz equation. First, the spatial variables and their partial derivatives are treated by interpolation basis functions, and the collocation method is established for solving second order differential equations. Then the differential matrix is employed to simplify the differential equations which is on a given test node. Finally, numerical experiments show the accuracy and effectiveness of the proposed method.

The numerical experiments show the advantages of the present method, such as less number of collocation nodes needed, shorter calculation time, higher precision, smaller error and higher efficiency. What is more, the numerical solutions agree well with the exact solutions.

Compared with finite element method, finite difference method and other traditional numerical methods based on grid solution, meshless method can reduce or eliminate the dependence on grid and make the numerical implementation more flexible.

The Helmholtz equation has a wide application background in many fields, such as physics, mechanics, engineering and so on.

This meshless method is first time applied for solving the 3D Helmholtz equation. What is more the present work not only gives the relationship of interpolation nodes but also the test nodes.

The purpose of this paper is to detect predefined service attributes and their sentiments from online restaurant reviews, and then to measure the effects of customer sentiments toward service attributes on customer satisfaction (CS) and revisit intention (RVI) simultaneously.

This study proposed a supervised framework to model CS and RVI simultaneously from restaurant reviews. Specifically, the authors detected the predefined service dimensions from online reviews based on random forest. Then, the sentiment polarities of the reviews toward each predefined dimension were identified using light-gradient boosting machine (LightGBM). Finally, the effects of attribute-specific sentiments on CS and RVI were evaluated by a bagged neural network-based model. The proposed framework was evaluated by 305,000 restaurant comments collected from DianPing.com, a Yelp-like website in China.

The authors obtained a hierarchal importance order of the investigated service themes (i.e. location, service, environment, price and food). The authors found that food played the most important role in affecting both CS and RVI. The most salient attribute with respect to each service theme was also identified.

Unlike prior work relying on the data collected from surveys, this study is among the first to model the relationship among service attributes, CS and RVI simultaneously from real-world data. The authors established a hierarchal structure of eighteen attributes within five service themes and estimated their effects on both CS and RVI, which will broaden our understanding of customer perception and behavioral intention during service consumption.

The purpose of this paper is to provide a new auto‐cooking industrial system for the Chinese food industry.

First, the paper introduces a robotic system with the redundant control functions based on the embedded RISC fieldbus control system IP core. Second, the data acquisition of the advanced cooks' operation procedure is used to get the teaching knowledge in the different cooking actions for the typical Chinese dishes. Finally, according to the teaching‐playback method, the auto‐cooking procedure for the complex Chinese dishes is completed well.

It is found that the new auto‐cooking system can cook many Chinese traditional dishes with high quality.

The robot is applicable to cooking automatically for the Chinese food industry.

The auto‐cooking industrial system has been developed with the programming method for the cooking actions.

The purpose of this paper is to recommend a validated numerical model for simulation the flue gases heat recovery recuperators. Due to fulfill of this demand, the influences of ash fouling characteristics during the transient/steady-state simulation and optimization of a 3D complex heat exchanger equipped with inner plain fins and side plate fins are studied.

For the particle dispersion modeling, the discrete phase model is applied and the flow field has been solved using SIMPLE algorithm.

According to obtained results, for the recuperator equipped with combine inner plain and side plate fins, determination of ash fouling characteristics is really important, effective and determinative. It is clear that by underestimating the ash fouling characteristics, the achieved results are wrong and different with reality.

Finally, the configuration with inner plain fins with characteristics of: d_i =5 mm, d_o = 6 mm, d_g = 2 mm, d_k = 3 mm and NIPFT = 9 and side plate fins with characteristics of: T_F = 3 mm, P_F = 19 mm, NSPF = 17·2 = 34, W_F = 10 mm, H_F = 25 mm, L_F = 24 mm and ß = 0° is introduced as the optimum model with the best performance among all studied configurations.