Sensor Training Data Reduction for Autonomous Vehicles

2019 ◽  
Author(s):  
Matthew Tomei ◽  
Alexander Schwing ◽  
Satish Narayanasamy ◽  
Rakesh Kumar
Keyword(s):  
Data Reduction ◽  
Autonomous Vehicles ◽  
Training Data

scholarly journals Real-Time Behaviour Planning and Highway Situation Analysis Concept with Scenario Classification and Risk Estimation for Autonomous Vehicles

Designs ◽  
2019 ◽  
Vol 3 (1) ◽  
pp. 4 ◽  
Author(s):  
Bence Dávid ◽  
Gergő Láncz ◽  
Gergely Hunyady
Keyword(s):  
Decision Making ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Risk Estimation ◽  
Training Data ◽  
Traffic Density ◽  
Support Vector ◽  
Situation Analysis ◽  
Probabilistic Networks ◽  
Time Operation

The development of autonomous vehicles is one of the most active research areas in the automotive industry. The objective of this study is to present a concept for analysing a vehicle’s current situation and a decision-making algorithm which determines an optimal and safe series of manoeuvres to be executed. Our work focuses on a machine learning-based approach by using neural networks for risk estimation, comparing different classification algorithms for traffic density estimation and using probabilistic and decision networks for behaviour planning. A situation analysis is carried out by a traffic density classifier module and a risk estimation algorithm, which predicts risks in a discrete manoeuvre space. For real-time operation, we applied a neural network approach, which approximates the results of the algorithm we used as a ground truth, and a labelling solution for the network’s training data. For the classification of the current traffic density, we used a support vector machine. The situation analysis provides input for the decision making. For this task, we applied probabilistic networks.

scholarly journals Deep Neural Networks for the Classification of Bank Marketing Data using Data Reduction Techniques

2019 ◽  
Vol 8 (3) ◽  
pp. 4373-4378
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Data Reduction ◽  
Deep Neural Network ◽  
Training Data ◽  
Neural Network Classifier ◽  
Data Set ◽  
Reduction Techniques ◽  
Marketing Data ◽  
Bank Marketing

The amount of data belonging to different domains are being stored rapidly in various repositories across the globe. Extracting useful information from the huge volumes of data is always difficult due to the dynamic nature of data being stored. Data Mining is a knowledge discovery process used to extract the hidden information from the data stored in various repositories, termed as warehouses in the form of patterns. One of the popular tasks of data mining is Classification, which deals with the process of distinguishing every instance of a data set into one of the predefined class labels. Banking system is one of the realworld domains, which collects huge number of client data on a daily basis. In this work, we have collected two variants of the bank marketing data set pertaining to a Portuguese financial institution consisting of 41188 and 45211 instances and performed classification on them using two data reduction techniques. Attribute subset selection has been performed on the first data set and the training data with the selected features are used in classification. Principal Component Analysis has been performed on the second data set and the training data with the extracted features are used in classification. A deep neural network classification algorithm based on Backpropagation has been developed to perform classification on both the data sets. Finally, comparisons are made on the performance of each deep neural network classifier with the four standard classifiers, namely Decision trees, Naïve Bayes, Support vector machines, and k-nearest neighbors. It has been found that the deep neural network classifier outperforms the existing classifiers in terms of accuracy

Training data reduction to speed up SVM training

2014 ◽  
Vol 41 (2) ◽  
pp. 405-420 ◽  
Author(s):  
Senzhang Wang ◽  
Zhoujun Li ◽  
Chunyang Liu ◽  
Xiaoming Zhang ◽  
Haijun Zhang
Keyword(s):  
Data Reduction ◽  
Training Data ◽  
Speed Up

scholarly journals Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4503
Author(s):  
Jose Roberto Vargas Rivero ◽  
Thiemo Gerbich ◽  
Boris Buschardt ◽  
Jia Chen
Keyword(s):  
Autonomous Vehicles ◽  
Data Augmentation ◽  
Synthetic Data ◽  
Real Data ◽  
Weather Conditions ◽  
Point Clouds ◽  
Training Data ◽  
Driver Assistance Systems ◽  
Solid Objects ◽  
Adverse Weather

In contrast to previous works on data augmentation using LIDAR (Light Detection and Ranging), which mostly consider point clouds under good weather conditions, this paper uses point clouds which are affected by spray. Spray water can be a cause of phantom braking and understanding how to handle the extra detections caused by it is an important step in the development of ADAS (Advanced Driver Assistance Systems)/AV (Autonomous Vehicles) functions. The extra detections caused by spray cannot be safely removed without considering cases in which real solid objects may be present in the same region in which the detections caused by spray take place. As collecting real examples would be extremely difficult, the use of synthetic data is proposed. Real scenes are reconstructed virtually with an added extra object in the spray region, in a way that the detections caused by this obstacle match the characteristics a real object in the same position would have regarding intensity, echo number and occlusion. The detections generated by the obstacle are then used to augment the real data, obtaining, after occlusion effects are added, a good approximation of the desired training data. This data is used to train a classifier achieving an average F-Score of 92. The performance of the classifier is analyzed in detail based on the characteristics of the synthetic object: size, position, reflection, duration. The proposed method can be easily expanded to different kinds of obstacles and classifier types.

scholarly journals Efficient data abstraction using weighted IB2 prototypes

2014 ◽  
Vol 11 (2) ◽  
pp. 665-678 ◽  
Author(s):  
Stefanos Ougiaroglou ◽  
Georgios Evangelidis
Keyword(s):  
Data Reduction ◽  
Training Data ◽  
Training Dataset ◽  
Data Abstraction ◽  
Prototype Selection ◽  
Initial Training ◽  
Reduction Techniques ◽  
Efficient Data ◽  
Data Reduction Technique ◽  
Better Than

Data reduction techniques improve the efficiency of k-Nearest Neighbour classification on large datasets since they accelerate the classification process and reduce storage requirements for the training data. IB2 is an effective prototype selection data reduction technique. It selects some items from the initial training dataset and uses them as representatives (prototypes). Contrary to many other techniques, IB2 is a very fast, one-pass method that builds its reduced (condensing) set in an incremental manner. New training data can update the condensing set without the need of the ?old? removed items. This paper proposes a variation of IB2, that generates new prototypes instead of selecting them. The variation is called AIB2 and attempts to improve the efficiency of IB2 by positioning the prototypes in the center of the data areas they represent. The empirical experimental study conducted in the present work as well as the Wilcoxon signed ranks test show that AIB2 performs better than IB2.

Sign in / Sign up

Export Citation Format

Share Document