In this paper some methods of dealing with the problem of cooperative learning in a multi-agent environment are presented. A system is developed that learns by reinforcement and deals with the problems of communicatio...
详细信息
To ensure reliable predictions for various applications, it is essential to understand the impact of Gaussian and non-Gaussian noise on data-driven modeling. Gaussian noise has been a convenient assumption for model d...
详细信息
The ability to explain the reasons for one's decisions to others is an important aspect of being human intelligence. We will look at the explainability aspects of the deep learning models, which are most frequentl...
详细信息
ISBN:
(纸本)9798350398823
The ability to explain the reasons for one's decisions to others is an important aspect of being human intelligence. We will look at the explainability aspects of the deep learning models, which are most frequently used in medical image processing tasks. The Explainability of machine learning models in medicine is essential for understanding how the particular ML model works and how it solves the problems it was designed for. The work presented in this paper focuses on the classification of lung CT scans for the detection of COVID-19 patients. We used CNN and DenseNet models for the classification and explored the application of selected visual explainability techniques to provide insight into how the model works when processing the images.
A wide variety of fieldbuses have been set up in the industrial automation system in different time periods under different environment. Therefore, during the development of industrial automation systems and control a...
详细信息
ISBN:
(纸本)0780378660
A wide variety of fieldbuses have been set up in the industrial automation system in different time periods under different environment. Therefore, during the development of industrial automation systems and control applications, the developer has to consider the interconnection of heterogeneous fieldbuses. In the paper, a Heterogeneous Fieldbuses Interconnection Architecture (HFIA) is presented to interconnect heterogeneous fieldbuses in wide area industrial automation system. The HFIA provides an integrated software framework to interconnect heterogeneous fieldbuses. With the help of the HFIA, it is easy and fast to interconnect heterogeneous fieldbuses. At the same time, the HFIA can be used for high-level industrial applications to control, monitor and optimize the operations of the fieldbuses systems. Profilbus, CANbus and Ethernet/IP are adopted as case studies for the HFIA architecture.
Regarding to global problem of ageing, mobile manipulator type of home service robot MARY (Mobile Assistant Robot for You) has been developed in the Department of Bioengineering and robotics, Tohoku University. The us...
详细信息
This paper aims to extract the computational logic of a hybrid method for online calibration of car-following models and apply it to a refined car-following model that incorporates the behavior of vehicles moving on t...
详细信息
ISBN:
(纸本)9798350398823
This paper aims to extract the computational logic of a hybrid method for online calibration of car-following models and apply it to a refined car-following model that incorporates the behavior of vehicles moving on the adjacent traffic lanes. This calibration method combines the concept of Kalman filters with the Takagi-Sugeno Fuzzy Inference System (T-S FIS). Furthermore, this paper analyzes the influence of the lane change behavior on the calibration process. The testing of the hybrid calibration method in the case of a refined car-following model uses real traffic data and it is followed by a discussion of the results based on day/night traffic behaviors.
This paper proposes self-localization and map building methods based on a steady-state genetic algorithm and self organizing map for a mobile robot used for illuminance measurement. According to the measured distance ...
详细信息
ISBN:
(纸本)9781424407897
This paper proposes self-localization and map building methods based on a steady-state genetic algorithm and self organizing map for a mobile robot used for illuminance measurement. According to the measured distance by a laser range finder, the map is updated sequentially. When the difference between the self-position on the building map and the estimated self-position baesd on the measured distance is larger than the predefined threshold, the proposed method corrects the self-location and updates the map to be more accurate. Finally we show experimental results of the proposed method.
An approach to intelligent process automation based on distributed planning agents is presented in this paper. According to this approach a higher-level agent-based automation layer supervises an ordinary process auto...
详细信息
ISBN:
(纸本)0780378660
An approach to intelligent process automation based on distributed planning agents is presented in this paper. According to this approach a higher-level agent-based automation layer supervises an ordinary process automation system. The purpose of the agent layer is to monitor the operation of the lower-level automation system and semi-autonomously reconfigure its control logic when needed. The agent layer operates as a distributed planning and plan execution system, which creates and runs reconfiguration sequences on the ordinary automation system in order to adapt it to various situations. In this way the approach aims to increase the operational flexibility of the whole automation system. The approach is demonstrated with a laboratory test process where process startup scenarios have been imitated. Experiences from the initial test runs are also described.
In order to realize the dual arm mobile robot control and simulation, a distributed robotic system is presented. The system provides the robot's model building, path planning, robot task planning, simulation and a...
详细信息
Unmanned Air Vehicles (UAVs) have several advantages and disadvantages compared with Unmanned Ground Vehicles (UGVs). Both systems have different mobility and perception abilities. UAV systems have extended perception...
详细信息
ISBN:
(纸本)9781424407897
Unmanned Air Vehicles (UAVs) have several advantages and disadvantages compared with Unmanned Ground Vehicles (UGVs). Both systems have different mobility and perception abilities. UAV systems have extended perception, tracking, and mobility capabilities compared with UGVs. UGVs have more intimate mobility and manipulation capabilities. This paper presents the research that has been conducted in the collaboration of UAVs and UGVs. This research demonstrates the use of a passive UAV system for tracking and state estimation of a UGV. This paper presents the UAV sensors and avionics, the algorithms for combining the UGV kinematics equations, and the geo-positioning algorithms used on the UAV to form a robust UGV state estimation. Experimental results are presented.
暂无评论