We have bio-chemically realized Artificial Intelligence by using DNA reactions, which is composed of a well-known as oscillating DNA reactions, the seesaw gate reaction. Through biochemical experiments, we confirm that mismatched interact-able DNA sequences can adapt to perturbations of environmental change, which is caused by making point mutation in an input sequence. Based on this result, we model this reaction by using abstract chemistry and confirm that the model exhibits the same behavior as biochemical experiments. Through computational simulations show that this DNA reaction can compose the logic gate bio-chemically.

View full abstract

Herein, we report on the development of a system for agent facial expression generation that uses vowel recognition when generating synthesized speech. The speech is recognized using the Julius high-performance, two-pass large vocabulary continuous speech recognition decoder software system, after which the agent’s facial expression is synthesized using preset parameters that depend on each vowel. The agent was created using MikuMikuDanceAgent (MMDAgent), which is a freeware animation program that allows users to create and animate movies with agents.

View full abstract

The design of the LLC resonant converter is presented for use in Electric discharge machining (EDM) applications. The converter is designed to operate with a 3phase ac input voltage and will output controlled dc voltages during the striking and arc conditions of EDM process. The method of the LLC resonant converter can operate at zero voltage and zero current transitions, we change the output current and control the current waveform of the EDM.

View full abstract

An FSK (Frequency-Shift Keying) based industrial analog signal transmission is proposed in this paper. Due to the advantage of digital transmission, such as noise immunity and error check, the digital transmission is more and more popular. The FSK is a simple kind of basic digital transmission. Although the analog signal modulation is already well-known and mature, but it is easily interfered by the noise, especially in an industrial environment. When the carried frequency is occupied, the alternative frequency is necessary. However, it is a tough work for sure. The FSK based wireless transmission is used to perform a wireless transmission of analog signal in the industry. It also has good effects of removing the wiring from device to device, and breaks the restriction of the device movement. Experimental results show that the proposed method can work well, and the wireless transmission bandwidth achieves 16kHz.

View full abstract

As a humanoid robot, the humanoid soccer robot integrates artificial intelligence with competitive sports skillfully. It is an intelligent control system which integrates mechanical structure, computer, circuit design, automatic control, decision-making, communication, and other technologies. In recent years, it is a very good research platform in the field of artificial intelligence and robots. This paper designs a humanoid soccer robot based on STM32 processor, and completes the theoretical analysis and experimental verification, the specific work is as follows:Through theoretical analysis and experimental verification, the stability, working parameters and the division and cooperation of STM32 and 51 series single-chip computers of humanoid soccer robot system are analyzed, and determine the final control scheme. STM32 drives the camera to collect information, process images and make decisions. STC12C5A60S2 controls the robot steering gear to complete the corresponding action. Serial communication is used between the two controllers. The peripheral circuit mainly includes OV7725 camera module and TFT-LCD LCD display module. In order to recognize and approach soccer by humanoid soccer robot and kick soccer into the goal, we should design the action programs such as straight walking, left turning, right turning, head scanning course, left translating, right translating and kicking. Reasonable images processing and decision algorithms are also designed. Finally, the control program is developed on Keil software platform for debugging. The experimental results show that the humanoid soccer robot designed in this paper can accurately identify the soccer ball and the goal, and accurately complete the kicking actions, which meets the relevant requirements of the expected design and scheme.

View full abstract

The polyurethane materials have been widely used in the field of antibacterial, medical, waterproof and moisture permeable. Therefore, this paper mainly studies on the determination of the film formation rate of polyurethane, and designs a film formation rate measuring instrument based on the Atmega328P single chip microcomputer and BH1750 light intensity measurement chip. This design compares the advantages and disadvantages of the currently widely used film formation rate measuring instrument and improves its multiple sensors into a high-precision main sensor. Measurement requirements are reduced, and the size of the instrument is also reduced, making it easier and more portable. Moreover, it can be used not only to measure the film formation rate of polyurethane, but also to determine the film formation rate of other materials.

View full abstract

In recent years, “Entertainment Computing” (EC) has attracted attention and has become one of the major industries in Japan. “Projection Mapping” is well known in this EC. Projection mapping is a video technology that creates a new space by synthesizing space and video using a projector. Among them, many people are fascinated by works that create a fantastic world by combining dancer performance and projection mapping. However, these works require the performer to accurately align with the coordinates of the image objects in the projection mapping, which is not easy for everyone. In this study, we aim to entertain not only the people who see the projection mapping but also performers. Therefore, we have prototyped an interactive projection mapping that changes according to user movement. This time, we focused on sports and projected the ball to the user to experience baseball pitching and soccer lifting. Furthermore, we conducted a questionnaire survey to evaluate the sense of use of this system, and the results showed that many people can enjoy by this projection mapping.

View full abstract

With the development of integrated electronic circuit manufacturing technology, enterprises have put forward higher requirements for the quality of silicon chips. Aiming at the low efficiency of silicon wafer defect detection, this paper proposes an automatic defect detection method based on machine vision. The voiding algorithm based on flood fill can effectively extract the inner contour information of the wafer profile. A rotation correction algorithm is proposed to correct the wafer yaw angle. The actual wafer was used to verify the performance of the proposed method. The results show that the proposed method is effective in detection accuracy.

View full abstract

We propose a new data augmentation method in automatic summarization system, especially the Pointer-Generator model. A large corpus is required to create an automatic summarization system using deep learning. However, in the field of natural language processing, especially in the field of automatic summarization, there are not many data sets that are sufficient to train automatic summarization system. Therefore, we propose a new method of data augmentation. We use the Pointer-Generator model. First, we determine the importance of each sentence in an article using topic model. In order to augment the data, we remove the least important sentence from an input article and use it as a new article. We examine the effectiveness of our proposed data augmentation method in automatic summarization system.

View full abstract

This paper proposes an autonomous mobile robot expected to realize an intelligent robot that supports a human life. The proposed mobile robot has three main functions; self-position estimation, road region estimation, and route planning. Self-position estimation is performed by comparing local features obtained from the frontal images captured by the robot to a knowledge base. In road region estimation, the frontal image is separated into several regions to find the region where the robot can move. Furthermore, the route to the destination is planned by graph search. Experimental results show satisfactory performance of the proposed mobile robot.

View full abstract