Passenger transport is one of the most common ways of commuting in Taiwan. It plays an important role in the transportation system due to its large number of stations, dense frequency, and cheap transportation. Due to...
详细信息
Passenger transport is one of the most common ways of commuting in Taiwan. It plays an important role in the transportation system due to its large number of stations, dense frequency, and cheap transportation. Due to...
Passenger transport is one of the most common ways of commuting in Taiwan. It plays an important role in the transportation system due to its large number of stations, dense frequency, and cheap transportation. Due to the unfriendly transportation environment and a large number of passengers, a blind spot of passenger transportation exists, which leads to traffic accidents at the station. We research to make the "Bus Stop Passenger Detection System". Taking the object detection of "Wheelchairs" into consideration, it is more convenient to assist the disabled to find the passenger transportation system, which makes Taiwan's transportation system more convenient.
Linear predictive coding is an extremely effective voice generation method that operates through simple process. However, linear predictive coding-generated voices have limited variations and exhibit excessive noise. ...
详细信息
Linear predictive coding is an extremely effective voice generation method that operates through simple process. However, linear predictive coding-generated voices have limited variations and exhibit excessive noise. To resolve these problems, this article proposes an artificial intelligence model that combines a denoise autoencoder with generative adversarial networks. This model generates voices with similar semantics through the random input from the latent space of generator. The experimental results indicate that voices generated exclusively by generative adversarial networks exhibit excessive noise. To solve this problem, a denoise autoencoder was connected to the generator for denoising. The experimental results prove the feasibility of the proposed voice generation method. In the future, this method can be applied in robots and voice generation applications to increase the humanistic language expression ability of robots and enable robots to demonstrate more humanistic and natural speaking performance.
This paper proposes an intelligent control strategy for enabling a robotic arm to grasp and place water-filled bottles without spilling any of the water. First, the system architecture of a five-degree-of-freedom robo...
详细信息
This paper proposes an intelligent control strategy for enabling a robotic arm to grasp and place water-filled bottles without spilling any of the water. First, the system architecture of a five-degree-of-freedom robotic arm and its mechanical design are introduced. Second, both the forward and inverse kinematics of the robotic arm are derived. The study conducted an experiment in which the designed and implemented robotic arm could grasp a bottle of water and move it to another place. However, if the acceleration or the orientation of the robotic arm were inappropriate, the water in the bottle may be spilled during the movement. Therefore, the proposed strategy applies an inertial measurement unit for obtaining relevant information. According to the obtained information, the velocity curves of each joint could be optimized by adaptive inertia weight and acceleration coefficients particle swarm optimization. Finally, the experimental results demonstrated the feasibility and effectiveness of the proposed method.
A cognition learning algorithm based on a deep belief network and inertia weight Particle Swarm Optimization (PSO) is presented and examined in a humanoid robot. The psychology concepts were adopted from Thinking, Fas...
详细信息
A cognition learning algorithm based on a deep belief network and inertia weight Particle Swarm Optimization (PSO) is presented and examined in a humanoid robot. The psychology concepts were adopted from Thinking, Fast and Slow by Daniel Kahneman. The human brain comprises two systems, System 1 and System 2. Based on their characteristics, System 1 and System 2 handle different tasks during cerebration. In this study, Deep Belief Network (DBN) is trained to construct the function of System 1 for the rapid reaction. On the other hand, PSO is applied to build System 2 for the slow and complicated brain behavior. Through the cooperation of System 1 and System 2, the proposed cognition learning algorithm can apply the psychology theories to allow the humanoid robot for learning the suitable pitching postures autonomously. In the experiments conducted in this study, the robot was trained for only five selected points and was then asked to throw precisely to nine points. The proposed algorithm provided 100% accuracy in the robot pitching game. The feasibility of the proposed algorithm was thus verified.
Active magnetic bearings (AMBs) have been gradually developed and used in industrial applications. For a milling spindle system with full magnetic support, at least one axial AMB and two radial AMBs should be included...
详细信息
Active magnetic bearings (AMBs) have been gradually developed and used in industrial applications. For a milling spindle system with full magnetic support, at least one axial AMB and two radial AMBs should be included. As a result, the milling spindle dimensions will probably be too large for the application of machine tools. A multi-hybrid AMB design, in which one axial AMB, one radial AMB, and a permanent magnet (PM) are combined, is reported in this work. The PM is embedded for axial suspension for the rotor weight so that the force requirement and the dimensions of the axial AMB can be reduced. On the other hand, magnetic channels were specially designed to couple the three magnetic loops generated by the AMBs and PM instead of isolating these magnetic fluxes individually. The proposed design is also suitable for applications of robot arm joints, such as waist and shoulder joints, to improve the bearing lifetime under heavy loads and to actively regulate the joint position deviation. The proposed multi-hybrid AMB design was practically manufactured after intensive analyses and verified by practical tests.
With the fast expansion of renewable energy system installed capacity in recent years, the availability, stability, and quality of smart grids have become increasingly important. The renewable energy output forecastin...
详细信息
With the fast expansion of renewable energy system installed capacity in recent years, the availability, stability, and quality of smart grids have become increasingly important. The renewable energy output forecasting applications have also been developing rapidly in recent years, and such techniques have particularly been applied in the fields of wind and solar photovoltaic (PV). In the case of solar PV output forecasting, many applications have been performed with machine learning and hybrid techniques. In this paper, we propose a high-precision deep neural network model named PVPNet to forecast PV system output power. The methodology behind the proposed model is based on deep neural networks, and the model is able to generate a 24-h probabilistic and deterministic forecasting of PV power output based on meteorological information, such as temperature, solar radiation, and historical PV system output data. The forecasting accuracy of PVPNet is determined by the mean absolute error (MAE) and root mean square error (RMSE) values. The results from the experiments show that the MAE and RMSE of the proposed algorithm are 109.4845 and 163.1513, respectively. The results prove that the prediction accuracy of the PVPNet outperforms other benchmark models, and the algorithm also effectively predicts complex time series with a high degree of volatility and irregularity.
In recent years, the opposed high-speed gas bearing system has been gradually valued and used in the field of precision machinery, especially for precision instruments and mechanisms requiring high speed, high precisi...
详细信息
In recent years, the opposed high-speed gas bearing system has been gradually valued and used in the field of precision machinery, especially for precision instruments and mechanisms requiring high speed, high precision, and high rigidity. Although the bearing capacity is not as good as the oil film bearings, it can provide a working environment where the rotor can generate high speed and low heat without deformation of the shaft, and the gas pressure distribution of clearance in bearing also has better stability. Due to the strong nonlinearity of the gas film pressure function of gas bearings and the fact that the actual shaft system possesses dynamic problems including critical speed, spindle imbalance or improper bearing design, it will cause the rotation process of the shaft to produce a nonperiodic motion and instability, and even chaotic motion under certain parameters. And these irregular movements can even cause machine damage or process delays when serious, so in order to understand the process of working under the conditions where the system will have a nonperiodic phenomenon and to avoid the occurrence of irregular vibration especially chaos. In this paper, the opposed high-speed gas bearing system feature will be discussed in detail with three different numerical analysis methods, i.e. the finite difference method, perturbation method, and mixing method. The relevant theories include dynamic trajectories, spectrum analysis, bifurcation diagram, Poincare map, and the maximum Lyapunov exponents. From the results of nonlinear dynamic behavior of the rotor center, periodic and nonperiodic motions occur at different rotor masses and bearing parameters, respectively. Especially, for the chaos of shaft exists at specific intervals and can be distinguished efficiently. Meanwhile, it is found to ensure that the bearing system can suppress the phenomena of chaos actively by adjusting the bearing parameters, and reduce the system loss caused by irregular vibration.
robots must be able to recognize human emotions to improve the human-robot interaction (HRI). This study proposes an emotion recognition system for a humanoid robot. The robot is equipped with a camera to capture user...
详细信息
robots must be able to recognize human emotions to improve the human-robot interaction (HRI). This study proposes an emotion recognition system for a humanoid robot. The robot is equipped with a camera to capture users' facial images, and it uses this system to recognize users' emotions and responds appropriately. The emotion recognition system, based on a deep neural network, learns six basic emotions: happiness, anger, disgust, fear, sadness, and surprise. First, a convolutional neural network (CNN) is used to extract visual features by learning on a large number of static images. Second, a long short-term memory (LSTM) recurrent neural network is used to determine the relationship between the transformation of facial expressions in image sequences and the six basic emotions. Third, CNN and LSTM are combined to exploit their advantages in the proposed model. Finally, the performance of the emotion recognition system is improved by using transfer learning, that is, by transferring knowledge of related but different problems. The performance of the proposed system is verified through leave-one-out cross-validation and compared with that of other models. The system is applied to a humanoid robot to demonstrate its practicability for improving the HRI.
In the modern power market, electricity trading is an extremely competitive industry. More accurate price forecast is crucial to help electricity producers and traders make better decisions. In this paper, a novel met...
详细信息
暂无评论