Narrow Results

In the field of fashion design, consumers are increasingly demanding personalized and customized clothing, and the traditional design process relies on the experience and inspiration of designers, which is time-consuming and costly. Therefore, a study on the generation of artistic patterns in fashion design based on style transfer is put forward. Hand-held camera was used instead of traditional industrial camera or digital camera for image acquisition. On the basis of bilateral filtering, weight variable values were set by adaptive method, and Inceptionv3 model was used to classify clothing design art patterns. On the basis of the style transfer algorithm, the pre-trained VGG-19 model was used for feature extraction, and the bidirectional mapping performance of Cycle GAN was utilized to construct the art pattern generation model while retaining the input image features. The experimental results show that the loss function value of the design method is kept below 0.5, the search time is 0.28s, the running time is always lower than 0.2s, and the fitness value is higher than 80. Therefore, this method effectively improves the design efficiency, reduces the cost, and meets the needs of consumers for personalized design, providing strong support for automation and intelligence in the field of clothing design.

An ensemble performs well when the component classifiers are diverse yet accurate, so that the failure of one is compensated for by others. A number of methods have been investigated for constructing ensemble in which some of them train classifiers with the generated patterns. This study investigates a new technique of training pattern generation. The method alters input feature values of some patterns using the values of other patterns to generate different patterns for different classifiers. The effectiveness of neural network ensemble based on the proposed technique was evaluated using a suite of 25 benchmark classification problems, and was found to achieve performance better than or competitive with related conventional methods. Experimental investigation of different input values alteration techniques finds that alteration with pattern values in the same class is better for generalization, although other alteration techniques may offer more diversity.

Regular array grammars (RAGs) are the lowest subclass in the Chomsky-like hierarchy of isometric array grammars. The left-hand side of each rewriting rule of RAGs has one nonterminal symbol and at most one "#" (a blank symbol). Therefore, the rewriting rules cannot sense contexts of non-# symbols. However, they can sense # as a kind of context. In this paper, we investigate this #-sensing ability. and study the language generating power of RAGs. Making good use of this ability, We show a method for RAGs to sense the contexts of local shapes of a host array in a derivation. Using this method, we give RAGs which generate the sets of all solid upright rectangles and all solid squares. On the other hand. it is proved that there is no context-free array grammar (and thus no RAG) which generates the set of all hollow upright rectangles.

Terminal weights are attached to L-systems by replacing each terminal generated by an OL-system by f_a(i) in the ith step of a derivation. The family of terminal weighted OL languages will be equal to the recursively enumerable set. Terminal weights are attached to EOL-regular matrix languages and also to OL array languages. Parquet deformations are generated by TWEOL-RMS.

A formal model for three-dimensional object representation is introduced. It uses parallel techniques and significantly reduces the time required for dealing with three-dimensional image analysis problems. Its fundamental properties are investigated and several interesting examples are illustrated.

We introduce a sequential/parallel parsing algorithm for analyzing 3-dimensional polyhedral objects represented by 3-d universal array grammars. The mechanism serves as a compromise between purely sequential methods, which normally take too much time, and purely parallel methods, which take too much hardware for large digital arrays. Several examples of 3-d polyhedral objects of various shapes and their corresponding parsing sequences are illustrated. Future research topics are discussed.

This work investigates three-dimensional pattern generation problems and their applications to three-dimensional Cellular Neural Networks (3DCNN). An ordering matrix for the set of all local patterns is established to derive a recursive formula for the ordering matrix of a larger finite lattice. For a given admissible set of local patterns, the transition matrix is defined and the recursive formula of high order transition matrix is presented. Then, the spatial entropy is obtained by computing the maximum eigenvalues of a sequence of transition matrices. The connecting operators are used to verify the positivity of the spatial entropy, which is important in determining the complexity of the set of admissible global patterns. The results are useful in studying a set of global stationary solutions in various Lattice Dynamical Systems and Cellular Neural Networks.

A simple scalar coupled map lattice (sCML) model for excitable media is derived in this paper. The new model, which has a simple structure, is shown to be closely related to the observed phenomena in excitable media. Properties of the sCML model are also investigated. Illustrative examples show that this kind of model is capable of reproducing the behavior of excitable media and of generating complex spatiotemporal patterns.

This paper describes about selective deposition of material for pattern generation. The process is carried out using masking technique and by deposition of constituent material of powder metallurgical (P/M) green compact tool at selected area of aluminium work surface in Electro Discharge Machining (EDM) process. The process is carried out to generate line pattern with a hard layer of tungsten and copper at the selected area. Thus, it can improve surface integrity of aluminium substrate while maintaining its overall lightness. P/M tool, positive polarity of tool and hydrocarbon dielectric are used to achieve appreciable amount of material transfer from tool to work surface. The average deviation of material deposition from predefined boundary line is evaluated as edge roughness of the pattern. Taguchi Design of Experiment is used to perform Analysis of Variance (ANOVA) and Overall Evaluation Criteria (OEC) for its parametric study. The surface roughness is obtained in the range of 4.7–10.55$\mu$m and edge roughness in the range of 36.49–56.82$\mu$m in various working conditions. However, surface roughness of 4.00$\mu$m and edge roughness of 21.47$\mu$m are achieved at the optimum condition.

It has previously been shown that resistance fluctuations in resistive sensors provide enhanced sensitivity and selectivity for gas detection. We report measurements and analysis of non-Gaussian components in nanoparticle Pd_z(WO₃)_1-z film gas sensors, with z being 0.01 or 0.12, in different ambients. These components can be characterized by higher-order spectra. Contour plots are given of bispectra, and plots of integrated bispectra and trispectra. The phase of the integrated higher-order spectra is analyzed as well.

This paper discusses the generation of a running pattern for a biped and verifies the validity of the proposed method of running pattern generation via experiments. When a running pattern is created with resolved momentum control, the angular momentum of the robot at the Center of Mass (COM) is set to zero, as the angular momentum causes the robot to rotate. However, this also induces unnatural motion of the upper body of the robot. To resolve this problem, the biped was set to a virtual under-actuated robot with a free joint at its support ankle, and a fixed point for a virtual system was determined. Following this, a new periodic running pattern was formulated using the fixed point. The fixed point is easily determined using a numerical approach. In an experiment, the planar biped ran forward using the proposed pattern generation method for running. Its maximum velocity was 2.88 km/h. In the future, faster running of the biped will be realized in a planar plane and the biped will run in an actual environment.

This paper discusses the generation of a running pattern for a humanoid biped and verifies the validity of the proposed method of running pattern generation via experiments. Two running patterns are generated independently in the sagittal plane and in the frontal plane and the two patterns are then combined. When a running pattern is created with resolved momentum control in the sagittal plane, the angular momentum of the robot about the Center of Mass (COM) is set to zero, as the angular momentum causes the robot to rotate. However, this also induces unnatural motion of the upper body of the robot. To solve this problem, the biped was set as a virtual under-actuated robot with a free joint at its support ankle, and a fixed point for a virtual under-actuated system was determined. Following this, a periodic running pattern in the sagittal plane was formulated using the fixed point. The fixed point is easily determined in a numerical approach. In this way, a running pattern in the frontal plane was also generated. In an experiment, a humanoid biped known as KHR-2 ran forward using the proposed running pattern generation method. Its maximum velocity was 2.88 km/h.

A formal model for three-dimensional object representation is introduced. It uses parallel techniques and significantly reduces the time required for dealing with three-dimensional image analysis problems. Its fundamental properties are investigated and several interesting examples are illustrated.

Regular array grammars (RAGs) are the lowest subclass in the Chomsky-like hierarchy of isometric array grammars. The left-hand side of each rewriting rule of RAGs has one nonterminal symbol and at most one “#” (a blank symbol). Therefore, the rewriting rules cannot sense contexts of non-# symbols. However, they can sense # as a kind of context. In this paper, we investigate this #-sensing ability, and study the language generating power of RAGs. Making good use of this ability, we show a method for RAGS to sense the contexts of local shapes of a host array in a derivation. Using this method, we give RAGs which generate the sets of all solid upright rectangles and all solid squares. On the other hand, it is proved that there is no context-free array grammar (and thus no RAG) which generates the set of all hollow upright rectangles.

We introduce a sequential/parallel parsing algorithm for analyzing 3-dimensional polyhedral objects represented by 3-d universal array grammars. The mechanism serves as a compromise between purely sequential methods, which normally take too much time, and purely parallel methods, which take too much hardware for large digital arrays. Several examples of 3-d polyhedral objects of various shapes and their corresponding parsing sequences are illustrated. Future research topics are discussed.