Traditional pattern making models are mainly linear models. This kind of model has many shortcomings. As Back Propagation (BP) neural network using simple nonlinear transfer functions can approximate any nonlinear fun...
详细信息
ISBN:
(纸本)9789813146969
Traditional pattern making models are mainly linear models. This kind of model has many shortcomings. As Back Propagation (BP) neural network using simple nonlinear transfer functions can approximate any nonlinear functions with any precision, we proposed a BP neural network model to predict all pattern making- related body dimensions by inputting few key human body dimensions. Sixty students in the northeast of China were measured for collecting a learning data to train the proposed model, and eleven of the sixty subjects' body dimensions data were applied to test the accuracy of the model. The results show that the prediction accuracies of linear regression model and BP neural network model have little difference. As the traditional linear model can be well applied in pattern making, the BP neural network model also can be well used for pattern making. Moreover, if increasing the number of learning samples, the precision of the proposed model is further improved.
In this paper, a rule based representation with interval certitude structure is presented as well as its inference method based on evidential reasoning, operational research and fuzzy set theory. A rule base is design...
详细信息
ISBN:
(纸本)9789813146969
In this paper, a rule based representation with interval certitude structure is presented as well as its inference method based on evidential reasoning, operational research and fuzzy set theory. A rule base is designed with interval certitude degrees embedded in the antecedent terms and consequent terms, which is shown to be capable of capturing uncertainties of human knowledge and human judgment. And the evidential reasoning approach is applied to the rule combination.
Predicting the market value of a residential property accurately without inspection by professional valuer could be beneficial for vary of organization and people. Building an Automated Valuation Model could be benefi...
详细信息
ISBN:
(纸本)9789813146969
Predicting the market value of a residential property accurately without inspection by professional valuer could be beneficial for vary of organization and people. Building an Automated Valuation Model could be beneficial if it will be accurate adequately. This paper examined 47 machine learning models (linear and non-linear). These models are fitted on 1967 records of units from 19 suburbs of Sydney, Australia. The main aim of this paper is to compare the performance of these techniques using this data set and investigate the effect of spatial information on valuation accuracy. The results demonstrated that tree models named eXtreme Gradient Boosting Linear, eXtreme Gradient Boosting Tree and Random Forest respectively have best performance among other techniques and spatial information such drive distance and duration to CBD increase the predictive model performance significantly.
In this work, a new algorithm for describing the quality of fiber spatial distribution in nonwoven structures using image analysis and a multicriteria approach is presented. The method is based on the spatial classifi...
详细信息
ISBN:
(纸本)9789813146969
In this work, a new algorithm for describing the quality of fiber spatial distribution in nonwoven structures using image analysis and a multicriteria approach is presented. The method is based on the spatial classification of the surface area into three categories: "normal" density of fiber, "low" density of fiber and "high" density of fiber. A multicriteria characterization is then computed from this first image analysis classification taking into account human knowledge and expertise.
In this study we compare cotton and polyester (Polyethylene terephthalate) (PET) sensory attributes, as a precursor for sensory modification of polyester, for cotton replacement. We systematically identify the key sen...
详细信息
ISBN:
(纸本)9789813146969
In this study we compare cotton and polyester (Polyethylene terephthalate) (PET) sensory attributes, as a precursor for sensory modification of polyester, for cotton replacement. We systematically identify the key sensory attributes that distinguish cotton from polyester fabrics. Rank Aggregation, Principal Component Analysis (PCA), Agglomerative Hierarchical Clustering (AHC), and the measure of distances are used to process elicited data.
The aim of this study is to show what type of basic fuzzy time series (TS) models was the most accurate in the set of data CIF 2015 competition organized in the framework of IFSA - EUSFLAT 2015 conference. Three types...
详细信息
ISBN:
(纸本)9789813146969
The aim of this study is to show what type of basic fuzzy time series (TS) models was the most accurate in the set of data CIF 2015 competition organized in the framework of IFSA - EUSFLAT 2015 conference. Three types of fuzzy TS models were investigated: model, based on fuzzified TS values, model, based on fuzzified first differences of TS values and model, based on the elementary fuzzy tendencies. In the study forecasting accuracy of these fuzzy TS models analyzed in dependence of different characters of TS.
In this paper we propose alpha-lock paramodulation for a lattice-valued logic LnF(X), which is a refined method for alpha-paramodulation. Firstly the concepts and their equivalence of E-alpha-interpretation and alpha-...
详细信息
ISBN:
(纸本)9789813146969
In this paper we propose alpha-lock paramodulation for a lattice-valued logic LnF(X), which is a refined method for alpha-paramodulation. Firstly the concepts and their equivalence of E-alpha-interpretation and alpha-equality axioms set are extended. Then the concept of alpha-lock paramodulation is given, and its properties are shown. Finally its soundness and completeness are established.
In this paper, we focused on the Integrated Process Planning and Scheduling (IPPS) which was an example of job-shop scheduling problem. Several approaches were proposed to solve this problem and Ant Colony Optimizatio...
详细信息
ISBN:
(纸本)9789813146969
In this paper, we focused on the Integrated Process Planning and Scheduling (IPPS) which was an example of job-shop scheduling problem. Several approaches were proposed to solve this problem and Ant Colony Optimization (ACO) was one of the widely used approaches. Examining the articles in which ACO algorithm was described and applied to the IPPS problem gave us an insight of current performance of optimization algorithms to this problem. We then proposed a Genetic Algorithm (GA) for the problem and implemented both algorithms, ACO and GA, in Javascript. According to the results, increasing the running time of GA leaded to more optimal results than ACO. In addition, GA found better results compared to ACO in small-scale problems. On the other hand, ACO performed better than GA in limited time or in bigger problems. In this paper, we proposed a GA approach for IPPS problems. Our chromosome model had 2 parts;first part represented machines of processes and second part showed the orders of the jobs. We applied different mutation/crossover types to these parts and then determined better parameters with numerous experiences. Also, we created an iOS application for visually comparing this GA approach with an ACO algorithm previously proposed. Our GA approach gave better results in some problem types. Our application could be downloaded in the following link (iPad was recommended): https://***/co/app/ipps-solver/id876097527? l=en&mt=8
Public bike sharing systems have been recently implemented in many big cities around the world. They are one of the solutions to face many public transport problems, including traffic congestion, air pollution, global...
详细信息
ISBN:
(纸本)9789813146969
Public bike sharing systems have been recently implemented in many big cities around the world. They are one of the solutions to face many public transport problems, including traffic congestion, air pollution, global oil prices and global warming. Despite the apparent success of these systems, their exploitation and management imply crucial operational challenges while few scientific works are available to support such complex dynamical systems. The balancing of stations is the most crucial question for their operational efficiency and economic viability. In this paper, we address the problem of balancing of stations with multiple vehicles by considering the static case. A mathematical formulation of the problem is proposed. Two solving methods based on genetic and memetic algorithms are developed. The experiments are performed on a large set of instances.
暂无评论