The glass swing: a vector active structure made of glass struts and 3D-printed steel nodes

The majority of glass used in load-bearing structures is as planar elements. Some projects exist that use linear glass elements. This paper discusses in broad terms the design, engineering, and fabrication of a unique vector active glass structure consisting of glass bundles and partly printed steel connections. A structure was conceived that utilizes the glass bundles in a way that can be directly experienced by the users: a swing. To create a non-standard form for the swing, a structural optimization procedure was used. To realize the structure, a novel steel node was developed and produced using an additive manufacturing technique in steel. These novel applications have made the project innovation heavy, particularly considering the limited timeframe for its development and construction. Description is given of the several optimization techniques incorporated in the digital process, the assembly and testing of the glass bundles, and the manufacturing of the steel nodes by Wire and Arc Additive Manufacturing.

Toward an Effective Combination of multiple Visual Features for Semantic Image Annotation

In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.

Optimal cooperative path planning of unmanned aerial vehicles by a parallel genetic algorithm

SUMMARYThe current paper presents a path planning method based on probability maps and uses a new genetic algorithm for a group of UAVs. The probability map consists of cells that display the probability which the UAV will not encounter a hostile threat. The probability map is defined by three events. The obstacles are modeled in the probability map, as well. The cost function is defined such that all cells are surveyed in the path track. The simple formula based on the unique vector is presented to find this cell position. Generally, the cost function is formed by two parts; one part for optimizing the path of each UAV and the other for preventing UAVs from collision. The first part is a combination of safety and length of path and the second part is formed by an exponential function. Then, the optimal paths of each UAV are obtained by the genetic algorithm in a parallel form. According to the dimensions of path planning, genetic encoding has two or three indices. A new genetic operator is introduced to select an appropriate pair of chromosome for crossover operation. The effectiveness of the method is shown by several simulations.