다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Objective Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

https://iopscience.iop.org/article/10.1088/1741-2552/ab0ab5/pdf

Deep learning for electroencephalogram (EEG) classification tasks: a review.

Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.

SeqSLAM : visual route-based navigation for sunny summer days and stormy winter nights

To generate local trajectory between initial states and target states for autonomous vehicles, a feasible trajectory generation algorithm based on quartic Bezier curve is proposed. The problem of trajectory generation is firstly separated into generating continuous and bounded curvature profile to shape the trajectory and generating linear velocity profile to execute the trajectory. The curvature profile generation is further converted to an optimization problem with only 3 parameters owing to the specific properties of quartic Bezier curve. Sequential quadratic programming is employed to find optimal solution with respect to specific objective function. To avoid sideslip and ensure velocityncontinuity and acceleration limits, the framework of linear velocity profile generation is also proposed. A simple profile with constant acceleration is also provided as an example. Simulation results on lane keeping and changing and path following demonstrate the capability and the realntime performance of the proposed algorithm.

Quartic Bezier curve based trajectory generation for autonomous vehicles with curvature and velocity constraints

Space manipulators are flexible structures. Vibration problem will be unavoidable due to motion or external disturbance excitation. Model based control methods will not maintain the required accuracy because of the existence of nonlinear factors and parameter uncertainties. To solve these problems, fuzzy logic control laws with different membership function groups are adopted to suppress vibrations of a flexible smart manipulator using collocated piezoelectric sensor/actuator pair. Also, dual-mode controllers combining fuzzy logic and proportional integral control are designed, for suppressing the lower amplitude vibration near the equilibrium point significantly. Experimental comparison research is conducted, using fuzzy control algorithms and the dual-mode controllers with different membership functions. The experimental results show that the adopted fuzzy control algorithms can substantially suppress the larger amplitude vibration; and the dual-mode controllers can also damp out the lower amplitude vibration significantly. The experimental results demonstrate that the proposed fuzzy controllers and dual-mode controllers can suppress vibration effectively, and the optimal placement is feasible.

Experimental Comparison Research on Active Vibration Control for Flexible Piezoelectric Manipulator Using Fuzzy Controller

The aerial manipulator is a special and new type of flying robot composed of a rotorcraft unmanned aerial vehicle (UAV) and a/several manipulator/s. It has gained a lot of attention since its initial appearance in 2010. This is mainly because it enables traditional UAVs to conduct versatile manipulating tasks from air, considerably enriching their applications. In this survey, a complete and systematic review of related research on this topic is conducted. First, various types of structure designs of aerial manipulators are listed out. Subsequently, the modeling and control methods are introduced in detail from the perspective of two types of typical application cases: free-flight and motion-restricted operations. Finally, challenges for future research are presented.

Survey on Aerial Manipulator: System, Modeling, and Control

The normal unscented Kalman filter (UKF) suffers from performance degradation and even divergence while mismatch between the noise distribution assumed to be known as a priori by UKF and the true ones in a real system. In this paper, a novel adaptive UKF (AUKF) is developed and applied to nonlinear joint estimation of both time-varying states and parameters. A cost function is built based on the error between the covariance matrices of innovation and their corresponding estimations. An adaptive algorithm is then designed to online update the covariance of the process noise by minimizing the cost function. The updated covariance is further fed back into the normal UKF. As a result of using such an adaptive mechanism, the robustness of conventional UKF is substantially improved with respect to the uncertain and time-varying noise covariance in the real system. To illustrate this mechanism, simulations are conducted on the dynamics of an unmanned helicopter by jointly estimating both the states and model errors. The improvements of the proposed AUKF are demonstrated by comparing the results with and without the adaptive mechanism.

Jianda Han

Papers

Quartic Bezier curve based trajectory generation for autonomous vehicles with curvature and velocity constraints

Experimental Comparison Research on Active Vibration Control for Flexible Piezoelectric Manipulator Using Fuzzy Controller

Survey on Aerial Manipulator: System, Modeling, and Control

A novel adaptive unscented Kalman filter for nonlinear estimation

Angular acceleration estimation and feedback control: An experimental investigation