scholarly journals Verification of End to End Learning Concept for Mobile Robotics Platform [Kennesaw State University]

2019 ◽  
Author(s):  
Vivian Nguyen ◽  
Kevin McFall
Keyword(s):  
Mobile Robotics ◽  
Autonomous Driving ◽  
Training Data ◽  
Sensor Data ◽  
Validation Dataset ◽  
Raspberry Pi ◽  
Human Observer ◽  
State University ◽  
End To End ◽  
Fully Connected

End-to-end neural networks (EENN) utilize machine learning to make predictions or decisions without being explicitly programmed to perform tasks by considering the inputs and outputs directly. In contrast, traditional hard coded algorithmic autonomous robotics require every possibility programmed. Existing research with EENN and autonomous driving demonstrates level-two autonomy where the vehicle can assist with acceleration, braking, and environment monitoring with a human observer, such as NVIDIA's DAVE-2 autonomous car system by utilizing case-specific computing hardware, and DeepPiCar by scaling technology down to a low power embedded computer (Raspberry Pi). The goal of this study is to recreate previous findings on a different platform and in different environments through EENN application by scaling up DeepPiCar with a NVIDIA Jetson TX2 computing board and hobbyist grade parts (e.g. 12V DC motor, Arduino) to represent 'off-the-shelf' components when compared to DAVE-2. This advancement validates that the concept is scalable to using more generalized data, therefore easing the training process for an EENN by avoiding dataset overfitting and production of a system with a level of 'common sense'. Training data is collected via camera input and associating velocity and encoder values from a differential drive ground vehicle (DDGV) with quadrature motors at 320x240 resolution with a CSV database. Created datasets are fed into an EENN analogous to the DAVE-2 EENN layered structure: one normalization, five convolutional, three fully connected layers. The EENN is considered a convolutional neural network (assumes inputs are images and learns filters, e.g. edge detection, independently from a human programmer), and accuracy is measured by comparing produced velocity values against actual values from a collected validation dataset. An expected result is the DDGV navigates a human space and obstacles by the EENN only inputting sensor data and outputting velocities for each motor

End-to-End Multi-Task Machine Learning of Vehicle Dynamics for Steering Angle Prediction for Autonomous Driving

2019 ◽  
Author(s):  
Nicholas Merrill ◽  
Azim Eskandarian
Keyword(s):  
Network Architecture ◽  
Autonomous Driving ◽  
Sensor Data ◽  
Dynamic Information ◽  
Steering Angle ◽  
Robust Algorithms ◽  
Error Accumulation ◽  
End To End ◽  
Traditional Approaches ◽  
Quality Maps

Abstract The traditional approaches to autonomous, vision-based vehicle systems are limited by their dependency on robust algorithms, sensor fusion, detailed scene construction, and high-quality maps. End-to-end models offer a means of circumventing these limitations by directly mapping an image input to a steering angle output for lateral control. Existing end-to-end models, however, either fail to capture temporally dynamic information or rely on computationally expensive Recurrent Neural Networks (RNN), which are prone to error accumulation via feedback. This paper proposes a Multi-Task Learning (MTL) network architecture that leverages available dynamic sensor data as a target for auxiliary tasks. This method improves steering angle prediction by facilitating the extraction of temporal dependencies from sequentially stacked image inputs. Evaluations performed on the publicly available Comma.ai dataset show a 28.6% improvement in steering angle prediction over existing end-to-end methods.

Cardiology Fellowship Education in the Era of High-density Training, Data Tracking, and Quality Measures

2011 ◽  
Vol 9 (2) ◽  
pp. 99
Author(s):  
Alex J Auseon ◽  
Albert J Kolibash ◽  
◽  
Keyword(s):  
Ohio State University ◽  
Training Data ◽  
State University ◽  
Training Requirements ◽  
Healthcare Environment ◽  
Medical Centers ◽  
Work Hour ◽  
The Ohio State University ◽  
Data Tracking

Background:Educating trainees during cardiology fellowship is a process in constant evolution, with program directors regularly adapting to increasing demands and regulations as they strive to prepare graduates for practice in today’s healthcare environment.Methods and Results:In a 10-year follow-up to a previous manuscript regarding fellowship education, we reviewed the literature regarding the most topical issues facing training programs in 2010, describing our approach at The Ohio State University.Conclusion:In the midst of challenges posed by the increasing complexity of training requirements and documentation, work hour restrictions, and the new definitions of quality and safety, we propose methods of curricula revision and collaboration that may serve as an example to other medical centers.

DeepSSPred: A Deep Learning Based Sulfenylation site predictor via a novel n-segmented optimize federated feature encoder

2020 ◽  
Vol 27 ◽  
Author(s):  
Zaheer Ullah Khan ◽  
Dechang Pi
Keyword(s):  
Large Scale ◽  
Computational Models ◽  
Research Work ◽  
Training Data ◽  
Training Dataset ◽  
Validation Dataset ◽  
Cytokine Signaling ◽  
Minority Class ◽  
Independent Dataset ◽  
Feature Encoding

Background: S-sulfenylation (S-sulphenylation, or sulfenic acid) proteins, are special kinds of post-translation modification, which plays an important role in various physiological and pathological processes such as cytokine signaling, transcriptional regulation, and apoptosis. Despite these aforementioned significances, and by complementing existing wet methods, several computational models have been developed for sulfenylation cysteine sites prediction. However, the performance of these models was not satisfactory due to inefficient feature schemes, severe imbalance issues, and lack of an intelligent learning engine. Objective: In this study, our motivation is to establish a strong and novel computational predictor for discrimination of sulfenylation and non-sulfenylation sites. Methods: In this study, we report an innovative bioinformatics feature encoding tool, named DeepSSPred, in which, resulting encoded features is obtained via n-segmented hybrid feature, and then the resampling technique called synthetic minority oversampling was employed to cope with the severe imbalance issue between SC-sites (minority class) and non-SC sites (majority class). State of the art 2DConvolutional Neural Network was employed over rigorous 10-fold jackknife cross-validation technique for model validation and authentication. Results: Following the proposed framework, with a strong discrete presentation of feature space, machine learning engine, and unbiased presentation of the underline training data yielded into an excellent model that outperforms with all existing established studies. The proposed approach is 6% higher in terms of MCC from the first best. On an independent dataset, the existing first best study failed to provide sufficient details. The model obtained an increase of 7.5% in accuracy, 1.22% in Sn, 12.91% in Sp and 13.12% in MCC on the training data and12.13% of ACC, 27.25% in Sn, 2.25% in Sp, and 30.37% in MCC on an independent dataset in comparison with 2nd best method. These empirical analyses show the superlative performance of the proposed model over both training and Independent dataset in comparison with existing literature studies. Conclusion : In this research, we have developed a novel sequence-based automated predictor for SC-sites, called DeepSSPred. The empirical simulations outcomes with a training dataset and independent validation dataset have revealed the efficacy of the proposed theoretical model. The good performance of DeepSSPred is due to several reasons, such as novel discriminative feature encoding schemes, SMOTE technique, and careful construction of the prediction model through the tuned 2D-CNN classifier. We believe that our research work will provide a potential insight into a further prediction of S-sulfenylation characteristics and functionalities. Thus, we hope that our developed predictor will significantly helpful for large scale discrimination of unknown SC-sites in particular and designing new pharmaceutical drugs in general.

Cloning Safe Driving Behavior for Self-Driving Cars using Convolutional Neural Networks

2019 ◽  
Vol 12 (2) ◽  
pp. 120-127 ◽  
Author(s):  
Wael Farag
Keyword(s):  
Gradient Descent ◽  
Autonomous Driving ◽  
Driving Behavior ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Safe Driving ◽  
Processing Pipeline ◽  
Self Driving Cars ◽  
And Training

Background: In this paper, a Convolutional Neural Network (CNN) to learn safe driving behavior and smooth steering manoeuvring, is proposed as an empowerment of autonomous driving technologies. The training data is collected from a front-facing camera and the steering commands issued by an experienced driver driving in traffic as well as urban roads. Methods: This data is then used to train the proposed CNN to facilitate what it is called “Behavioral Cloning”. The proposed Behavior Cloning CNN is named as “BCNet”, and its deep seventeen-layer architecture has been selected after extensive trials. The BCNet got trained using Adam’s optimization algorithm as a variant of the Stochastic Gradient Descent (SGD) technique. Results: The paper goes through the development and training process in details and shows the image processing pipeline harnessed in the development. Conclusion: The proposed approach proved successful in cloning the driving behavior embedded in the training data set after extensive simulations.

Fully automated contrast and non-contrast cardiac view detection in echocardiography a multi-centre, multi-vendor study

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Gao ◽  
D Stojanovski ◽  
A Parker ◽  
P Marques ◽  
S Heitner ◽  
...  
Keyword(s):  
Neural Network ◽  
Training Data ◽  
Classification Model ◽  
Validation Dataset ◽  
Funding Source ◽  
Private Company ◽  
Validation Data ◽  
Independent Test ◽  
Model Training ◽  
Confusion Matrices

Abstract Background Correctly identifying views acquired in a 2D echocardiographic examination is paramount to post-processing and quantification steps often performed as part of most clinical workflows. In many exams, particularly in stress echocardiography, microbubble contrast is used which greatly affects the appearance of the cardiac views. Here we present a bespoke, fully automated convolutional neural network (CNN) which identifies apical 2, 3, and 4 chamber, and short axis (SAX) views acquired with and without contrast. The CNN was tested in a completely independent, external dataset with the data acquired in a different country than that used to train the neural network. Methods Training data comprised of 2D echocardiograms was taken from 1014 subjects from a prospective multisite, multi-vendor, UK trial with the number of frames in each view greater than 17,500. Prior to view classification model training, images were processed using standard techniques to ensure homogenous and normalised image inputs to the training pipeline. A bespoke CNN was built using the minimum number of convolutional layers required with batch normalisation, and including dropout for reducing overfitting. Before processing, the data was split into 90% for model training (211,958 frames), and 10% used as a validation dataset (23,946 frames). Image frames from different subjects were separated out entirely amongst the training and validation datasets. Further, a separate trial dataset of 240 studies acquired in the USA was used as an independent test dataset (39,401 frames). Results Figure 1 shows the confusion matrices for both validation data (left) and independent test data (right), with an overall accuracy of 96% and 95% for the validation and test datasets respectively. The accuracy for the non-contrast cardiac views of >99% exceeds that seen in other works. The combined datasets included images acquired across ultrasound manufacturers and models from 12 clinical sites. Conclusion We have developed a CNN capable of automatically accurately identifying all relevant cardiac views used in “real world” echo exams, including views acquired with contrast. Use of the CNN in a routine clinical workflow could improve efficiency of quantification steps performed after image acquisition. This was tested on an independent dataset acquired in a different country to that used to train the model and was found to perform similarly thus indicating the generalisability of the model. Figure 1. Confusion matrices Funding Acknowledgement Type of funding source: Private company. Main funding source(s): Ultromics Ltd.

scholarly journals End-to-End Autonomous Driving Through Dueling Double Deep Q-Network

2021 ◽  
Author(s):  
Baiyu Peng ◽  
Qi Sun ◽  
Shengbo Eben Li ◽  
Dongsuk Kum ◽  
Yuming Yin ◽  
...  
Keyword(s):  
Neural Network ◽  
State Space ◽  
Learning Algorithm ◽  
Rapid Development ◽  
Autonomous Driving ◽  
Saliency Map ◽  
Hierarchical Architecture ◽  
Link Type ◽  
The Neural Network ◽  
End To End

AbstractRecent years have seen the rapid development of autonomous driving systems, which are typically designed in a hierarchical architecture or an end-to-end architecture. The hierarchical architecture is always complicated and hard to design, while the end-to-end architecture is more promising due to its simple structure. This paper puts forward an end-to-end autonomous driving method through a deep reinforcement learning algorithm Dueling Double Deep Q-Network, making it possible for the vehicle to learn end-to-end driving by itself. This paper firstly proposes an architecture for the end-to-end lane-keeping task. Unlike the traditional image-only state space, the presented state space is composed of both camera images and vehicle motion information. Then corresponding dueling neural network structure is introduced, which reduces the variance and improves sampling efficiency. Thirdly, the proposed method is applied to The Open Racing Car Simulator (TORCS) to demonstrate its great performance, where it surpasses human drivers. Finally, the saliency map of the neural network is visualized, which indicates the trained network drives by observing the lane lines. A video for the presented work is available online, https://youtu.be/76ciJmIHMD8 or https://v.youku.com/v_show/id_XNDM4ODc0MTM4NA==.html.

scholarly journals BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2144
Author(s):  
Stefan Reitmann ◽  
Lorenzo Neumann ◽  
Bernhard Jung
Keyword(s):  
Point Clouds ◽  
Training Data ◽  
Sensor Data ◽  
Generation Process ◽  
Data Generation ◽  
Depth Sensor ◽  
Depth Sensing ◽  
Depth Sensors ◽  
3D Point Clouds ◽  
Wide Range

Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the training data generation process for a wide range of domains, we have developed the BLAINDER add-on package for the open-source 3D modeling software Blender, which enables a largely automated generation of semantically annotated point-cloud data in virtual 3D environments. In this paper, we focus on classical depth-sensing techniques Light Detection and Ranging (LiDAR) and Sound Navigation and Ranging (Sonar). Within the BLAINDER add-on, different depth sensors can be loaded from presets, customized sensors can be implemented and different environmental conditions (e.g., influence of rain, dust) can be simulated. The semantically labeled data can be exported to various 2D and 3D formats and are thus optimized for different ML applications and visualizations. In addition, semantically labeled images can be exported using the rendering functionalities of Blender.

Sign in / Sign up

Export Citation Format

Share Document