Search

A novel compliant z-stage is applied for positioning and indenting a specimen in nano/microindentation testing system. For an excellent operation, the proposed z-stage can concurrently satisfy multicriteria comprising high safety factor, small parasitic motion, and large output displacement. The key aims of this article are to present a novel design of the compliant z-stage as well as an effective integration methodology of Taguchi method, response surface method, weight factor calculation based on signal to noise, and the whale optimization algorithm to resolve a design optimal problem so as to enrich the quality performances of the proposed stage. Primarily, the z-stage is designed based on four-lever amplifier, compliant hinge shifted arrangement mechanism, zigzag-based flexure spring guiding mechanism, and symmetric six leaf hinges-based parallel guiding mechanism. Secondly, the number experiment data are achieved by the Taguchi method and finite element analysis. Subsequently, the regression functions among input variables and quality characteristics are formed by exploiting response surface method. In addition, the weight factors for every characteristic are defined. Additionally, the sensitivity analysis is accomplished for determining influences of input variables on quality responses. Ultimately, based on regression equations, the whale optimization algorithm is executed to define the optimal factors. The consequences indicated that the output deformation is about 454.55 μm and the safety factor is around 2.38. Furthermore, the errors among the optimal consequences and the confirmations for the safety factor and output deformation are 7.12% and 4.25%, correspondingly. By using Wilcoxon and Friedman methods, the results revealed that the proposed algorithm is better than the cuckoo search algorithm. Based on the quality convergence characteristics of hybrid approach, the proposed method is proficient for resolving complicated multiobjective optimization.

Research that applies artificial intelligence (AI) to generate the captions for an image has been extensively studied in recent years. However, the length of these captions was short, and the number of generated captions was limited. In addition, it is unknown whether a short story can be generated based on the image, because many sentences have to be connected to create a fluent short story. As a result, this study introduces an encoder-decoder framework structure to generate a short story captioning (SSCap) using a common image caption dataset and a manually collected story corpus. This manuscript has three main contributions, which include 1) an unsupervised deep learning-based framework that combines a recurrent neural network (RNN) structure and encoder-decoder model for composing a short story for an image, 2) a huge story corpus, which includes two different genres (horror and romantic), manually collected and validated. Extensive experiments demonstrated that short stories created by the proposed model show creative content compared to existing systems that can only make concise sentences. Therefore, the demonstrated framework has the potential to motivate the development of a more robust AI story writer and motivates the integration of the suggested model into practical applications to help the story writers find a new idea.

The nanoindentation technique is employed to characterize the behaviors of biomaterials. Nevertheless, there is a lack of development of a miniaturized precise positioner for in situ nanoindentation. Besides, modeling behaviors of the positioner are restricted due to its complex kinematic characteristics. Therefore, this paper proposes a novel compliant two degrees of freedom (dof) stage for positioning a biomaterial sample in in situ nanoindentation. In addition, a new modeling and dimensional optimization synthesis method of the stage is developed. The proposed effective methodology is developed based on a kinetostatic analysis-based calculation method, the Lagrange approach, and a neural network algorithm. With an increased advance in artificial intelligence, a neural network algorithm is proposed to extend the applicability of artificial neural networks in optimizing the parameters of the stage. First, the 2-dof stage is built via a combination of an eight-lever displacement amplifier and a symmetric parallelogram mechanism. Second, a chain of mathematical equations of the 2-dof stage is constructed using a kinetostatic analysis-based method to calculate the ratio of displacement amplification and the input stiffness of the 2-dof stage. Then, the Lagrange method is utilized to formulate the dynamic equation of the 2-dof stage. Finally, a neural network algorithm is adopted to maximize the natural first frequency of the proposed stage. The optimal results determined that the frequency of the stage can achieve a high value of 112.0995 Hz. Besides, the formed mathematical models were relatively precise by comprising the simulation verifications.

This paper devotes a new method in modeling and optimizing to handle the optimization of the XY positioning mechanism. The fitness functions and constraints of the mechanism are formulated via proposing a combination of artificial neural network (ANN) and particle swarm optimization (PSO) methods. Next, the PSO is hybridized with the grey wolf optimization, namely PSO-GWO, which is applied to three scenarios in handling the single objective function. In order to search the multiple functions for the mechanism, the multiobjective optimization genetic algorithm (MOGA) is applied to the last scenario. The achieved results showed that the fitness functions are well-formulated using the PSO-based ANN method. In the scenario 1, the stroke achieved by the PSO-GWO (1852.9842 μm) is better than that gained from the GWO (1802.8087 μm). In the scenarios 2, the stress gained from the PSO-GWO (243.3183 MPa) is lower than that achieved from the GWO (245.0401 MPa). In the scenario 3, the safety factor retrieved from the PSO-GWO (1.9767) is greater than that achieved from the GWO (1.9278). In the scenario 4, by using MOGA, the optimal results found that the stroke is about (1741.3 μm) and the safety factor is 1.8929. The prediction results are well-fitted with the numerical and experimental verifications. The results of this paper are expected to facilitate the synthesis and analysis of compliant mechanisms and related engineering designs.

With the advancement of bioengineering and robotic engineering, medical robots have been increasing concern about manipulating the microobject or cells. Although the rigid robots have a stable operation, they inherit many limitations such as the complex assembly process of joints-coupled rigid links and expensive costs. Especially, clearances between kinematic joints cause vibrations that damage microobject. To cope with such problems, a flexure-based polylactic acid (PLA) gripper is developed to realize precise motion in medical robots. The proposed gripper is 3D printed by fused deposition modeling technique with advantages of monolithic structure, jointless and cheap cost. Prior to the gripper fabrication, the optimization development of the gripper is conducted employing a combination of the non-parametric regression (NPR) and multi-objective genetic algorithm (MOGA). Numerical data samples are collected by the finite element method. The modeling results were well formulated utilizing the NPR method with the R2 value greater than 0.9. The Pareto-optimum design results identified that the gripper can provide a high displacement of 2 mm and a small stress of 41 MPa via MOGA. Additionally, the proposed flexure-based compliant PLA gripper can work with a safety factor higher than 1.6. The experiment tests on the prototype of the gripper are close to the estimated values.

This paper develops a hybrid optimization approach for multi-criteria optimal design of a compliant positioning platform for nanoindentation tester. The platform mimics the biomechanical behavior of beetle so as to allow a linear motion. Structure of the beetle-liked mechanism consists of six legs arranging in a symmetric topology. Amplification ratio and static characteristics of the platform are analyzed by finite element analysis (FEA). To improve the performances of the platform, the main geometric parameters of the platform are optimized by an efficient hybrid approach of the Taguchi method (TM), response surface methodology (RSM), improved adaptive neuro-fuzzy inference system (ANFIS), and teaching learning based optimization (TLBO). Numerical data are collected by integrating of the RSM and FEA. Signal to noise ratios are determined and the weight factor of each response is calculated. The suitable ANFIS’s parameters are optimized through the TM. The results found that trapezoidal-shaped MFs is the best type for the safety factor and the displacement. The optimal ANFIS’s parameters for the safety factor and the displacement were determined at the number of input MFs of 4, trapmf, hybrid learning method, and linear output MFs. According to improved ANFIS establishments, TLBO algorithm is utilized for solving the multi-objective optimization. Analysis of variance and sensitivity are investigated to determine the significant effects of design factors on the responses. The simulated and experimental validations are in a good agreement with the predicted results.

A Compliant XY micropositioning stage is purported for situating a material sample in nanoindentation tester process. This paper aims to develop, analyze and optimize a XY compliant micropositioning stage. The working stroke of proposed XY stage is amplified by combining the four-lever and a bridge amplification mechanism. To enhance the performances of the stage, the main geometric parameters are optimized by an integration method of Taguchi method, response surface method (RSM) and genetic algorithm (GA). Firstly, static analysis and dynamic analysis are conducted by the finite element analysis in order to predict initial performances of the XY stage. Secondly, the number of experiments and the data are retrieved by combination of the finite element analysis-integrated Taguchi method. Thirdly, the effects of main design variables on the output response sensitivity are considered. Later on, mathematical model for the amplification ratio was established by the RSM. Finally, based on the mathematical equation, the GA is adopted to define the optimal design variables. The results of numerical validations are in a good agreement with the predicted results. The results depicted that the proposed hybrid approach ensures a high reliability for engineering optimization problems.

This chapter deals with fracture mechanics of composites reinforced with short carbon and glass fibers. A short carbon fiber-reinforced polyamide 66 (SCFR-PA66) with 20 wt% fibers is introduced firstly. Then, dynamic fracture properties of the short glass fiber-reinforced polyamide 66 with 30 wt% of fibers (SGFR-PA66) are discussed. The influences of moisture on the fracture behavior of these materials are investigated through experimental studies. The impact properties of specimens are analyzed using a Charpy impact instrument. The fracture tests in the edgewise position of specimens are performed using Standard ISO 179. The results indicated that the moisture greatly affects the dynamic energy release rate of both materials. SGFR-PA66 has a higher dynamic energy release rate than SCFR-PA66. In addition, the dynamic energy release rate of both materials can be achieved at the same value when the moisture exceeds 2.4%. Finally, the fracture mechanism of SCFR-PA66 was investigated and analyzed. The energy release rate GIC of SCFR-PA66 was calculated to determine and predict the fracture properties of the material for the unidirectional short fiber composite.

In this article, an effective multiobjective optimization approach is exploited to search for the best milling parameters for CNC for complex 3d surfaces of SIMOLD 2083 alloy mold core. To improve the quality responses, the cutting factors are optimized by a combination of Taguchi method (TM), response surface method (RSM), and multiobjective water cycle algorithm (MWCA). Firstly, the design for initial series experiments of the cutting factors was generated via the TM. Thereafter, the regression models between the cutting factors and the surface roughness of the machined workpiece surface as well as milling time are formed via applying the RSM. Moreover, analysis of variance and sensitivity analysis are also executed to define the influences and crucial contributions of cutting parameters on the surface roughness and milling time. The results of analysis of variance showed that the factors which have main effects on surface roughness were spindle speed (42.42%), feed rate (29.40%), and cutting depth (6.59%), respectively. Meanwhile, the feed rate with the influence of 92.6% was the most significant factor in controlling the milling time. Ultimately, based on mathematical models, the MWCA is performed to define the optimal factors. The optimal results indicated that the optimized surface roughness was about 0.260 μm and the milling time was roughly 1012.767 (s). In addition, the errors between forecasted results and experimental verifications for the surface roughness and milling time are 2.04% and 5.39%, respectively. Therefore, the results of experimental verifications are suitable with the forecasted results from the proposed optimization method. These results depicted that the proposed integration approach can define effectively the optimal cutting factors for CNC milling and expand to apply for complex multiobjective optimization problems.

This study evaluates the displacement sensitivity of a new compliant microgripper. The microgripper is designed based on a four-bar mechanism and the concept of a compliant mechanism. The effects of the width of the right circular hinge, the thickness of microgripper, and the material properties on the dis-placement sensitivity are considered via using the finite element method. In the beginning, the stress and deformation of the compliant microgripper are evaluated. Subsequently, the displacement of the microgripper is then analyzed. The results showed that the design parameter and the displacement sensitivity have a close relationship. To increase the grasping reliability and measure the displacement or force, a micro-displacement sensor is integrated with the proposed microgripper. Finally, the modeling and analysis of the proposed sensor are conducted.

Design, manufacture prosthetics for disabilities people is developing strongly and extensive in the world. Rapid prototyping (RP) technologies provide the ability to fabricate initial prototypes from various model materials. The purpose of this research is to investigate and analyze the strength of parts of the prosthesis by using Inventor software applications and fused deposition modeling (FDM). A 200 mc machine is utilized to produce socket and calves. Results of this research coincided with the requirements of prosthetic functions for disabled people who have a maximum load of 113 kg. A CAD drawing of socket and calves is built. And then, measurement instruments are set up to measure and establish the prosthetics manufacturing processes via the use of rapid prototyping methods. This application has many advantages and prospects in the near future as rapid prototyping machines.

While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is much faster. Taking advantage of this, we propose a novel architecture to fit a 3D garment template to a 3D body. Specifically, we build upon the recent progress in 3D point cloud processing with deep networks to extract garment features at varying levels of detail, including point-wise, patch-wise and global features. We fuse these features with those extracted in parallel from the 3D body, so as to model the cloth-body interactions. The resulting two-stream architecture, which we call as GarNet, is trained using a loss function inspired by physics-based modeling, and delivers visually plausible garment shapes whose 3D points are, on average, less than 1 cm away from those of a PBS method, while running 100 times faster. Moreover, the proposed method can model various garment types with different cutting patterns when parameters of those patterns are given as input to the network., Accepted to ICCV 2019

This paper proposes an effective hybrid optimization algorithm for multiobjective optimization design of a compliant rotary positioning stage for indentation tester. The stage is created with respect to the Beetle’s profile. To meet practical demands of the stage, the geometric parameters are optimized so as to find the best performances. In the present work, the Taguchi method is employed to lay out the number of numerical experiments. Subsequently, the finite element method is built to retrieve the numerical data. The mathematical models are then established based on the response surface method. Before conducting the optimization implementation, the weight factor of each response is calculated exactly. Based on the well-established models, the multiple performances are simultaneously optimized utilizing the teaching learning-based optimization. The results found that the weight factors of safety factor and displacement are 0.5995 (59.95%) and 0.4005 (40.05%), respectively. The results revealed that the optimal safety factor is about 1.558 and the optimal displacement is 2.096 mm. The validations are in good agreement with the predicted results. Sensitivity analysis is carried out to identify the effects of variables on the responses. Using the Wilcoxon’s rank signed test and Friedman test, the effectiveness of the proposed hybrid approach is better than that of other evolutionary algorithms. It ensures a good effectiveness to solve a complex multiobjective optimization problem.

Understanding patterns of variation from raw measurement data remains a central goal of shape analysis. Such an understanding reveals which elements are repeated, or how elements can be derived as structured variations from a common base element. We investigate this problem in the context of 3D acquisitions of buildings. Utilizing a set of template models, we discover geometric similarities across a set of building elements. Each template is equipped with a deformation model that defines variations of a base geometry. Central to our algorithm is a simultaneous template matching and deformation analysis that detects patterns across building elements by extracting similarities in the deformation modes of their matching templates. We demonstrate that such an analysis can successfully detect structured variations even for noisy and incomplete data.

A new compliant XY micropositioning stage is designed for locating a material sample during nanoindentation tester. This paper aims to design and optimize the proposed stage. The working travel of proposed stage is amplified via using the four-lever amplification mechanism. To improve the performances of the stage, the geometric parameters are optimized by an integration method of Taguchi method (TM), response surface method (RSM) and nondominated sorting genetic algorithm II (NSGA-II). Firstly, the number of experiment of four design variables were created by the TM. Subsequently, the output displacement and the first natural frequency are retrieved by finite element analysis (FEA). Then, the mathematical equations between four design variables and both responses is established by using the RSM. Eventually, based on mathematical equations, the NSGA-II is adopted to determine the optimal parameters. The results indicated that the optimized y-axis displacement was about 3.862 mm and the first natural frequency was approximately 45.983. The results of FEA validations are in a good agreement with the predicted results from the proposed approach. This result indicated that the integrated proposed approach ensures a high reliability for engineering optimization problems.

News articles serve the purpose of spreading company's information to the investors either consciously or unconsciously in their trading strategies on the stock market. Because of the immense growth of the internet in the last decade, the amount of financial articles have experienced a significant growth. It is important to analyze the information as fast as possible so they can support the investors in making the smart trading decisions before the market has had time to adjust itself to the effect of the information. This paper proposes an approach of using time series analysis and improved text mining techniques to predict daily stock market directions. Experiment results show that our system achieved high accuracy (up to 73%) in predicting the stock trends.

In this paper, we examined the effects of financial news on Ho Chi Minh Stock Exchange (HoSE) and we tried to predict the direction of VN30 Index after the news articles were published. In order to do this study, we got news articles from three big financial websites and we represented them as feature vectors. Recently, researchers have used machine learning technique to integrate with financial news in their prediction model. Actually, news articles are important factor that influences investors in a quick way so it is worth considering the news impact on predicting the stock market trends. Previous works focused only on market news or on the analysis of the stock quotes in the past to predict the stock market behavior in the future. We aim to build a stock trend prediction model using both stock news and stock prices of VN30 index that will be applied in Vietnam stock market while there has been a little focus on using news articles to predict the stock direction. Experiment results show that our proposed method achieved high accuracy in VN30 index trend prediction.

Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the body and garment shapes. Our network learns to mimic a Physics-Based Simulation (PBS) method while requiring two orders of magnitude less computation time. To train the network, we introduce loss terms inspired by PBS to produce plausible results and make the model collision-aware. To increase the details of the draped garment, we introduce two loss functions that penalize the difference between the curvature of the predicted cloth and PBS. Particularly, we study the impact of mean curvature normal and a novel detail-preserving loss both qualitatively and quantitatively. Our new curvature loss computes the local covariance matrices of the 3D points, and compares the Rayleigh quotients of the prediction and PBS. This leads to more details while performing favorably or comparably against the loss that considers mean curvature normal vectors in the 3D triangulated meshes. We validate our framework on four garment types for various body shapes and poses. Finally, we achieve superior performance against a recently proposed data-driven method., Accepted to be published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), July 2020. arXiv admin note: text overlap with arXiv:1811.10983

A shape grammar defines a procedural shape space containing a variety of models of the same class, e.g. buildings, trees, furniture, airplanes, bikes, etc. We present a framework that enables a user to interactively design a probability density function (pdf) over such a shape space and to sample models according to the designed pdf. First, we propose a user interface that enables a user to quickly provide preference scores for selected shapes and suggest sampling strategies to decide which models to present to the user to evaluate. Second, we propose a novel kernel function to encode the similarity between two procedural models. Third, we propose a framework to interpolate user preference scores by combining multiple techniques: function factorization, Gaussian process regression, autorelevance detection, and l 1 regularization. Fourth, we modify the original grammars to generate models with a pdf proportional to the user preference scores. Finally, we provide evaluations of our user interface and framework parameters and a comparison to other exploratory modeling techniques using modeling tasks in five example shape spaces: furniture, low-rise buildings, skyscrapers, airplanes, and vegetation.