Shenglin Mu

Restroom Human Detection Using One-Dimensional Brightness Distribution Sensor

As aging society problem goes serious; systems to confirm safety of elders in daily life are expected. In this paper, a sensor, which detects person localization without privacy offending, applying brightness distribution is realized. In the proposed design, the sensor is constructed with a line sensor and cylindrical lens to obtain one-dimensional brightness distribution. Comparing with conventional line sensors, CMOS area sensors are with low cost, and high sensitivity. Therefore, in the proposed sensor, the CMOS area sensor is applied as covered in certain areas physically, so that it behaves as a line sensor. The proposed sensor is able to obtain one-dimensional horizontal brightness distribution that is approximately equal to integration value of each vertical pixel line of two-dimensional image. By employing this method, the information of the target person’s position and movement status can be obtained without using two-dimensional detail texture image.

Intelligent IMC-PID control for ultrasonic motor

Ultrasonic motor (USM) causes serious characteristic changes during operation and contains non-linearity caused by frictions. To compensate the characteristics, the internal model control - proportional integral differential (IMC-PID) control which requires only one parameter setting beforehand is widely applied to the control of ultrasonic motor. However, there are limitations of control performance on the conventional fixed-gain type IMC-PID control. So, in this paper we propose an improved method of variable gain type IMC-PID control combined with neural network (NN). In this proposed method, the identification method is adopted to overcome serious characteristic changes and neural network is used to compensate non-linearity. And, the effectiveness of the proposed method has been confirmed by experiments.

Slit Type One-Dimensional Brightness Distribution Sensor

As aging society problem goes serious, systems to confirm to safety of elders in daily life are expected. In this paper, a sensor, which detects person localization without privacy offending, applying brightness distribution is proposed. In the proposed design, the sensor is constructed with a line sensor and slit to obtain one-dimensional brightness distribution. The proposed sensor is able to obtain one-dimensional brightness distribution that is approximately equal to integration value of each vertical pixel line of two-dimensional image. By employing this method, the information of the targets position and movement status can be obtained without using two-dimensional detail texture image. In this paper, the effectiveness of the proposed method is confirmed by experiments.

Detection range fitting of slit type Obrid-Sensor

As aging society problem goes severe, systems to confirm to safety of elders in daily life are expected to relieve burdensome safety confirmation tasks of care workers. In this paper, a sensor, which detects person localization without privacy offending, applying Obrid-Sensor is proposed. In the proposed design, the Obrid-Sensor is constructed with a line sensor and a slit to obtain one-dimensional brightness distribution. The proposed sensor is able to obtain one-dimensional brightness distribution that is approximately equal to integration value of each vertical pixel line of two-dimensional image. Meanwhile, the novel slit type Obrid-Sensor, which was constructed without Rod lens, is studied in this research. By employing the proposed sensor, the information of a subjects position and motion can be obtained without using two-dimensional texture image. The effectiveness of the proposed method is confirmed by experiments.

Position control of ultrasonic motor using PID-IMC combined with neural network based on probability

In this paper, a novel control scheme of PID type internal model control (PID-IMC) using neural network (NN) is proposed for the position control of ultrasonic motor (USM). In the proposed scheme, a new NN controller combined with particle swarm optimization (PSO) based on probability is introduced. The NN controller is employed for tuning the control parameter in PID-IMC for compensating the characteristic changes and non-linearity in USM. On one hand, the application of the proposed method avoids the Jacobian estimation in conventional back-propagation (BP) type NN. On the other hand, the PSO based on probability, originated from tribes-PSO, simplifies the PSO setting by reducing the parameters to be set in USM control. For confirming the effectiveness of the proposed method in position control, a group of experiments have been done on an existent USM servo system and the results are studied in this paper.

Intelligent control of USM using a modified NN with PSO

As aging society problem goes severe In not only Japan but also the whole world, more and more attentions are attracted to the social and welfare fields. Many researches on science and technology for elders are implemented in rencent years. With the background, there are a lot of needs for techonologies with novel features for improvement. In this paper, a control method with attractive features for the actuator of Ultrasonic Motors (USMs) is introduced. In medical and welfare areas, the USMs are expected to play more important roles owing to their special characteristics. In this research, an intelligent PID control method using Neural Network (NN) combined with type Particle Swarm Optimization (PSO) is developed for the control of USM. In the method, the intelligent controller is designed based on variable gain type PID control using NN. The learning of the NN unit is implemented by the PSO. The gains of PID control are adjusted by the proposed method in real-time. The effectiveness of the method is verified by experimental results.

Applications of ultrasonic sensors and obrid-sensor in safety confirmation system for elders

As the aging problem in Japan becomes more and more severe, there are requirements for labor and resources to take care of elders. For lightening the burden of care workers in safety confirmation of elders in daily life, systems to confirm safety of elders attract a lot of attentions in recent years. This paper reports a safety confirmation system for elders. In the proposed system, for detecting the motion of elders, the system employing Obrid-Sensor and ultrasonic sensor is reported for safety confirmation of elders in restroom. The applications of Obrid-Sensor and ultrasonic sensors ensured the motion detection with privacy protection. The effectiveness of the proposed method was confirmed by experiments.

Intelligent PID Control for USM Using PSO in Real-Time Environment

In this paper, an intelligent PID controller is proposed for ultrasonic motor (USM) in real-time environment. To overcome the problems of characteristic variation and non-linearity, an intelligent PID controller using neural network (NN) combined with particle swarm optimization (PSO) is studied. In the proposed method, an NN controller is designed for adjusting PID gains. The learning of NN is implemented by PSO updating the weights of NN on-line. By employing the proposed method, the characteristic changes and non-linearity of USM can be compensated effectively in real-time environment. The effectiveness of the method is confirmed by experiments.

Intelligent PID control based on PSO type NN for USM

Ultrasonic Motors (USMs) are a kind of actuators with attractive features. Owing to the features, they are expected to be applied widely in industrial fields. Especially, since they work well in or near MRI environment, they are expected to play more important roles in medical and welfare area. In this research, for the control of USM, an intelligent PID control method using Neural Network (NN) combined with type Particle Swarm Optimization (PSO) is developed. In the method, the intelligent controller is designed based on variable gain type PID control using NN. The learning of the NN unit is implemented by the PSO. The PID gains are adjusted by the intelligent controller in real-time environment. The effectiveness of the method is confirmed by experiments.

Ground material distinction method using reflection intensities obtained by ultrasonic sensor

In this research, we propose a method to distinguish different ground materials using the reflection intensities of the waves obtained by ultrasonic sensor. In previous research, the information obtained by ultrasonic sensor is only used for checking the existence of an object, and/or measuring the distance from an existent object. To go a step further, applying the information obtained by ultrasonic sensor, we designed a method to distinguish different ground materials according to different reflection intensities. Based on the method, a group of experiments have been implemented for distinguishing seven different ground materials in this research. According to the results of the experiments, it can be stated that different ground materials can be classified according to the particular reflection intensities. Furthermore, we can also use the particular reflection intensities for recognizing the roughness of different grounds in order to alert in dangerous situations.