Showing 49–60 of 142 results

  • A laser scanner based in-process inspection approach of thru-hole for drilling robotic system

    Open Access

    Abstract: An in-process hole inspection subsystem was integrated with the drilling robotic system, which is based on the line laser scanner installed near the end-effector. The proposed inspection approach is based on the image processing of 3D (three dimension) point cloud obtained from laser scanner driven by the robotic manipulator. The normal of measuring surface was detected from the 3D point data on the hole edge, which determines the feedback signal to the hardware to adjust the direction of laser beam. By normal adjusting algorithm, the laser scanner is driven by the robotic manipulator to achieve the normal direction of the measuring hole. Then, based on 2D (two dimension) point data, the least square ellipse fitting method was applied to compute the hole parameters, such as diameter, circularity and positioning of the hole. The designed approach was tested for its accuracy and robust in an example of through hole automatic inspection

    Keywords: line laser scanner, drilling robot, hole inspection, normal adjusting

  • The Design of Intelligent Vehicle System Based on STM32

    Open Access

    Abstract: This paper design a new vehicle system that has a function of storing path data. The main control chip of the intelligent vehicles system is STM32F103ZET6. The current position and direction of the vehicle are determined by means of path memory and position recognition. This system is rarely affected by the ground condition, so there is no need for any ground signs.

    Keywords: intellectual vehicles system, path memory, position recognition, STM32F103ZET6

  • Design and Experiments of Distributed Compliant Actuator for Industrial Robots

    Open Access

    Abstract: In order to reduce the torsional moment of the motor in Axis-2, the drive compensation devices can be used for the joint of industrial robots. The static balance compensation range of conventional balance cylinders is limited. Since of lacking in autonomy, continuity, and dynamics, balance cylinders cannot be used for compensation when load is various. The dynamic cylinder based on series elastic actuator (SEA) devices is designed to realize the automatic response of industrial robots when load is various, to obtain continuous dynamic compensation of the inertia moment and to achieve the optimum balance. Because SEA devices have features of dynamic adjustment and energy amplification, they can be used to realize balance compensation and reduce effectively the power requirement for the joint drive motor or even replace a motor of Axis-2. Thus, a new kind of flexible balance-drive device is constructed. In this paper, theoretical and experimental analyses of the dynamic model are conducted. The experimental results prove that the devices combine the effects of balancing cylinders and motors of Axis-2, as well as increasing load capacity and flexibility.

    Keywords: Industrial robot; Balance mechanism; Series elastic actuator; Distributed actuator

  • Accuracy Evaluation for Mental Health Indicator Based on Vocal Analysis in Noisy Environments

    Open Access

    Abstract: Mental health care is one of the important challenges in our modern stressful society. The authors proposed a method for measuring mental health based on the quality of the patient’s voice, and implemented a system that monitors the state of mental health based on voice during a phone conversation via smartphone. However, there has been little consideration of the analysis of mental health using voices in a noisy environment thus far. Therefore, this study investigated the impact of noise on the mental health indicator based on vocal analysis. The results showed that the mental health level was judged to be low when the analyzed voice included noise. The study also revealed that a decreased precision in the detection of utterances had a significant impact on mental health analysis.

    Keywords: Mental health care; noisy environment; vocal analysis

  • Visualization of Individual Feature Amount Appearing in Daily Performance Based on Electrostatic Induction

    Open Access

    Abstract: In this paper, a new technique to measure daily human body motion without using cameras and video images is presented. The change in the electric potential of the human body that is caused by the daily performance induces an electrostatic induction current in the electrode placed at a distance of a few meters from the human body. Using this technology, I have developed an effective non-contact technique for the detection of human daily performance by detecting the change in this human-generated body charge. This technique based on the detection of an electrostatic induction current of the order of approximately sub-picoamperes flowing through an electrode that is placed at a distance of 5 m from the subject. It is shown that the characteristics of the individual are included in walking motion, sitting on a chair and retiring motion. This technique effectively explains the behavior of the waveform of the electrostatic induction current flowing through a given measurement electrode through a capacitance model of the human body.

    Keywords: Daily performance, Electrostatic induction current, Non-contact measurement, Wavelet transform

  • Regional Distance-based k-NN Classification

    Open Access

    Abstract: The k-Nearest Neighbor (k-NN) is very simple and powerful approach to conceptually approximate real-valued or discrete-valued target function. Many researchers have recently approved that K-NN is a high-prediction accuracy algorithm for a variety of real-world systems using many different types of datasets. However, as we know, k-NN is a type of lazy learning algorithms as it has to compare to each of stored training examples for each observed instance. Besides, the prediction accuracy of k-NN is under the influence of K values. Mostly, the higher K values make the algorithm yield lower prediction accuracy according to our experiments. For these issues, this paper focuses on two properties that are to upgrade the classification accuracy by introducing Regional Distance-based k-NN (RD-kNN) and to speed up the processing time performance of k-NN by applying multi-threading approach. For the experiments, we used the real data sets (wine, iris, heart stalog, breast cancer, and breast tissue) from UCI machine learning repository. According to our test cases and simulations carried out, it was also experimentally confirmed that the new approach, RD-kNN, has a better performance than classical kNN.
    Keywords: k-NN, RD-kNN

  • A Stress Analysis Method using Poincaré Plot and Complex Correlation Measures for Wearable Health Devices

    Open Access

    Abstract: This paper attempts to develop a stress analysis method using short-term heart rate (HR) data obtained with wearable health devices. Evaluation method for stress analysis is very important for disease prevention and health promotion. Wearable health devices, such as smart phones and wristband fitness watches, are capable of measuring HR data using photoplethysmography technologies. In recent years, many new commodity devices have been issued and been used to obtain healthcare information, including HR data, in people’s everyday life. However, since HR data of wearable devices are recorded with uneven and relatively long sampling intervals, which are constrained by their hardware issues, it is difficult to apply traditional spectral analysis methods for the HR data. The proposed method evaluates HR data using a non-linear technique, Poincaré plot. As the number of points in a plot is restricted by the limited sampling features of wearable devices, this paper applies two stress analysis indices that are based on complex correlation measures of time-varying characteristics in Poincaré plots. On the other hand, the proposed method can investigate dynamic changes in stress levels of short-term (e.g., one minute) analysis duration. Mental stress induction experiments were conducted with nine subjects to validate the proposed method.

    Keywords: Stress analysis; Wearable health devices; Heart rate variability (HRV); Poincaré plot; Complex correlation measure (CCM)

  • Detection of Genes Patterns with an Enhanced Partitioning-Based DBSCAN Algorithm

    Open Access

    Abstract: Microarray datasets are enriched with numerous unknown gene expression patterns  that may have significant biological meaning. Detecting well-separated gene expression patterns is a critical task in microarray data analysis. The density-based spatial clustering DBSCAN  algorithm has been used to detect patterns with different shapes and sizes in many applications. However, the DBSCAN algorithm is time-consuming when used on big datasets, and microarray datasets are considered as big and complex datasets. Therefore, in this study, we modified the DBSCAN algorithm by combining it with a partitioning around medoids algorithm based on normalized and weighted Mahalanobis distance (NWM). The developed algorithm (NWM_PDBSCAN) was tested on selected microarray expression datasets, which were pre-processed prior to analysis. The results revealed an optimal cluster solution with different shapes and sizes. We further reduced the dataset sizes using a random sampling technique to enhance the performance of the DBSCAN algorithm. The proposed NWM_PDBSCAN algorithm performed ideally, and was evaluated using Dunn’s validity index.

    Keywords: Microarray data; Partitioning around medoids; DBSCAN; Normalized weighted Mahalanobis distance; Validity index; Pre-processing; Sampling; Number of clusters

  • Design and Application of the Electronic Lock for Bicycle

    Open Access

    Abstract: A new type of the anti-theft electronic lock with the lock bolt structure is designed, which can realize the function of locking and unlocking of the bicycle safely. The hardware system includes the STC-12C5A microcontroller, RFID card, data read/write module and mechanical lock structure. The system combined the non-contact RFID card reader and the lock structure. And the static mechanical property is analyzed to meet various situations. A number of actual test results showed that the electronic lock system is safe and reliable.

  • On Autonomous Driving: Combining Holistic and Feature based Localization Systems (Reasons and Advantages)

    Open Access

    Abstract: This paper highlights the importance of combining intensity and feature based localization systems in autonomous driving. The intensity based localization system is represented by calculating cross correlation between LIDAR and map images. The feature based system is integrated by extracting the lateral edges from the LIDAR and map images with respect to the heading angle. An edge matching technique is then applied to estimate the lateral position based on the common extracted features. The experimental results have verified that the estimation of the lateral and longitudinal positions has been improved against the changes of weather and environmental conditions by combining the image and edge matching results.

  • Development of Inshore Fishing UAV at Sea Based on Preliminary Assessment Result

    Open Access

    Abstract: This paper initiates and describes the development of an inshore fishing UAV at the seashore, where the UAV can communicate with its controller by sending all the information during its flight in real time to the base station. The operation distance of the UAV from the seashore is to the fishing point will be between 500 m to 1km. The navigation method is under investigation, which is to guide the UAV from the seashore to fishing points along a predefined path planning by avoiding sudden obstacles it may face.

  • Integration of Drone’ Communication into an ITS Network

    Open Access

    Abstract: This paper presents the concept of a highly-sophisticated network system using unmanned aerial vehicles, further named drones, and wireless networks for enhancing safety against natural disasters. The system consists of several drones and ground vehicles. Each vehicle has a wireless network unit, which employs the dual-mode Wireless Access in Vehicular Environment (WAVE) in the 700 MHz or 5 GHz band, with the goal of creating a multi-hop (more than three hops) ad hoc network. These features enable the system to facilitate rescue and relief operations in the event of a serious disaster. The proposed system represents an innovation in the field of mesh network systems, being based on a combination of ubiquitous drones and ground vehicles.