Automatic artist recognition of songs for advanced retrieval

Automatic recognition of artists is very important in acoustic music indexing, browsing, and contentbased acoustic music retrieving, but synchronously it is still a challenging errand to extract the most representative and salient attributes to depict diversiform artists. In this paper, we developed a novel system to complete the reorganization of artist automatically. The proposed system can efficiently identify the artist's voice of a raw song by analyzing substantive features extracted from both pure music and singing song mixed with accompanying music. The experiments on different genres of songs illustrate that the proposed system is possible.     

A modified genetic algorithm for product family optimization with platform specified by information theoretical approach

Many existing product family design methods assume a given platform, However, it is not an in-tuitive task to select the platform and unique variable within a product family. Meanwhile, most approachesare single-platform methods, in which design variables are either shared across all product variants or not atall. While in multiple-platform design, platform variables can have special value with regard to a subset ofproduct variants within the product family, and offer opportunities for superior overall design. An informationtheoretical approach incorporating fuzzy clustering and Shannon's entropy was proposed for platform variablesselection in multiple-platform product family. A 2-level chromosome genetic algorithm (2LCGA) was proposedand developed for optimizing the corresponding product family in a single stage, simultaneously determiningthe optimal settings for the product platform and unique variables. The single-stage approach can yield im-provements in the overall performance of the product family compared with two-stage approaches, in which thefirst stage involves determining the best settings for the platform and values of unique variables are found foreach product in the second stage. An example of design of a family of universal motors was used to verify theproposed method.     

Parallel processing based on ship maneuvering in identification of interaction force coefficients

The parallel processing based on the free running model test was adopted to predict the interac-tion force coefficients (flow straightening coefficient and wake fraction) of ship maneuvering. And the multi-population genetic algorithm (MPGA) based on real coding that can contemporarily process the data of freerunning model and simulation of ship maneuvering was applied to solve the problem. Accordingly the optimalindividual was obtained using the method of genetic algorithm. The parallel processing of multi-populationsolved the prematurity in the identification for single population, meanwhile, the parallel processing of the dataof ship maneuvering (turning motion and zigzag motion) is an attempt to solve the coefficient drift problem.In order to validate the method, the interaction force coefficients were verified by the procedure and thesecoefficients measured were compared with those ones identified. The maximum error is less than 5%, and theidentification is an effective method.     

Production balance of ship erection

A network plan model of ship erection was established based on the network planning technologyand the work-package breakdown system. The load-oriented production control method was introduced to buildup a throughput diagram model thus it is possible to describe the ship erection process numerically. Based onthe digitaiized models some cases of production balance of ship erection were studied and three balance indexeswere put forward, they are the load balance rate, the input manpower balance rate and the maximum gantrycrane operating times. Such an analytic method based on the balance evaluation is the important foundationfor digitization and intelligentization of shipyard production management.     

Structural intensity characterization of composite laminates subjected to impact load

Structural intensity (SI) characterization of composite laminates subjected to impact load was dis-cussed. The SI pattern of the laminates which have different fiber orientations and boundary conditions wasanalyzed. The resultant forces and velocities of the laminates were calculated, and the structural intensity wasevaluated. The SI streamlines of carbon fiber reinforced epoxy composite laminates and the steel plates werediscussed. The results show that the SI streamlines of the graphite/epoxy laminates are different from that ofthe steel plates, and the SI streamlines are influenced by the boundaries, the stacking sequence of the compositelaminates. The change of the historical central displacement of the graphite/epoxy laminates is fasten thanthat of the steel plates.     

Investigation on drag reduction of trucks

A study of the mechanism of fences was given to reduce drag by means of theoretical analysis, numerical simulation and experimental research. A 3D mathematical model has been developed based on computational fluid dynamics software Phoenics that was capable of handling steady state, 3D flow to simulate the flow field around the truck. The experiment made in a low speed wind tunnel is used as references for validation. By analyzing the results of calculation and experiment, the flowing mechanism of the flow field around the container truck and the drag-reducing mechanism of #-shaped fences on the truck are unveiled, which provides theoretical guidance to the aerodynamic formation designing and amelioration.     

Experimental study on seismic performance of tall building with steel transfer trusses located at a higher level

Based on a shaking table experiment of 1 : 25 scale frame-shearwall structure model with steel transfer trusses, the dynamic characteristics, seismic responses in elastic and elastic-plastic phases with de- structive forms of the structure were studied. It was observed that cracks were developed with earthquake wave acceleration increasing, but no severe crack was developed in the structure during the experiment. In the seismic responses caused by artificial wave, site wave and E1 Centro wave, that caused by the artificial wave is the most intense one. Displacement angle between steel transfer trusses is large, which means the transfer stories might be weak. However, the seismic performance of the steel transfer trusses is good and the overall structure can satisfy seismic fortification requirements in the region of intensity 6.     

Fiber concrete under temperature drop load with stochastic FEM

Plain concrete plate and fiber concrete plate subjected to temperature drop load were analyzed on stochastic finite element method （FEM）. It is found that fibers can enhance concrete ability to resist temperature drop load for improving concrete＇s fracture energy and deferring the crack process. It is found for concrete not to improve apparently its tensile strength and fracture energy is recommended to be its appraisal parameter.     

Performance-driven routing tree construction with buffer insertion and wire sizing

A new approach was proposed to construct a performance-driven rectilinear Steiner tree with simultaneous buffer insertion and wiresizing optimization （PDRST/BW） under a higher order resistance-inductancecapacitance （RLC） delay model. This approach is based on the concept of sharing-buffer insertion and dynamic programming approach combined with a bottom-up rectilinear Steiner tree construction. The performances include the timing delay and the quality of signal waveform. The experimental results show that our proposed approach is scalable and obtains better performance than SP-tree and graph-RTBW approaches for the test signal nets.     

Children’s mode choice for the school trip: the role of distance and school location in walking to school

Rising levels of childhood obesity in the United States and a 75% decline in the proportion of children walking to school in the past 30 years have focused attention on school travel. This paper uses data from the US Department of Transportation’s 2001 National Household Travel Survey to analyze the factors affecting mode choice for elementary and middle school children. The analysis shows that walk travel time is the most policy-relevant factor affecting the decision to walk to school with an estimated direct elasticity of −0.75. If policymakers want to increase walking rates, these findings suggest that current policies, such as Safe Routes to School, which do not affect the spatial distribution of schools and residences will not be enough to change travel behavior. The final part of the paper uses the mode choice model to test how a land use strategy—community schools—might affect walking to school. The results show that community schools have the potential to increase walking rates but would require large changes from current land use, school, and transportation planning practices.