MICkNN:Multi-Instance Covering kNN Algorithm

Mining from ambiguous data is very important in data mining. This paper discusses one of the tasks for mining from ambiguous data known as multi-instance problem. In multi-instance problem, each pattern is a labeled bag that consists of a number of unlabeled instances. A bag is negative if all instances in it are negative. A bag is positive if it has at least one positive instance. Because the instances in the positive bag are not labeled, each positive bag is an ambiguous. The mining aim is to classify unseen bags. The main idea of existing multi-instance algorithms is to find true positive instances in positive bags and convert the multi-instance problem to the supervised problem, and get the labels of test bags according to predict the labels of unknown instances. In this paper, we aim at mining the multi-instance data from another point of view, i.e., excluding the false positive instances in positive bags and predicting the label of an entire unknown bag. We propose an algorithm called Multi-Instance Covering kNN （MICkNN） for mining from multi-instance data. Briefly, constructive covering algorithm is utilized to restructure the structure of the original multi-instance data at first. Then, the kNN algorithm is applied to discriminate the false positive instances. In the test stage, we label the tested bag directly according to the similarity between the unseen bag and sphere neighbors obtained from last two steps. Experimental results demonstrate the proposed algorithm is competitive with most of the state-of-the-art multi-instance methods both in classification accuracy and running time.

Structural form-finding of bending components in buildings by using parametric tools and principal stress lines

This paper aims to provide an efficient and straightforward structural form-finding method for designers to extrapolate component forms during the conceptual stage.The core idea is to optimize the classical method of structural form-finding based on principal stress lines by using parametric tools.The traditional operating process of this method relies excessively on the designer’s engineering experience and lacks precision.Meanwhile,the current optimization work for this method is overly complicated for architects,and limitations in component type and final result exist.Therefore,to facilitate an architect’s conceptual work,the optimization metrics of the method in this paper are set as simplicity,practicality,freedom,and rapid feedback.For that reason,this paper optimizes the method from three aspects:modeling strategy for continuum structures,classification processing of data by using the k-nearest neighbor algorithm,and topological form-finding process based on stress lines.Eventually,it allows architects to create structural texture with formal aesthetics and modify it in real time on the basis of structural analysis results.This paper also explores a comprehensive application strategy with internal force analysis diagramming to form-finding.The finite element analysis tool Karamba3D verifies the structural performance of the form-finding method.The performance is compared with that of the conventional form,and the comparison results show the practicality and potential of the strategy in this paper.