scholarly journals A Vehicle Detection Algorithm Based on Deep Belief Network

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Hai Wang ◽  
Yingfeng Cai ◽  
Long Chen
Keyword(s):  
Vehicle Detection ◽  
Detection Algorithm ◽  
Deep Belief Network ◽  
Data Sets ◽  
Belief Network ◽  
Deep Architecture ◽  
Critical Technology ◽  
Testing Data ◽  
Vehicle Active Safety ◽  
Better Than

Vision based vehicle detection is a critical technology that plays an important role in not only vehicle active safety but also road video surveillance application. Traditional shallow model based vehicle detection algorithm still cannot meet the requirement of accurate vehicle detection in these applications. In this work, a novel deep learning based vehicle detection algorithm with 2D deep belief network (2D-DBN) is proposed. In the algorithm, the proposed 2D-DBN architecture uses second-order planes instead of first-order vector as input and uses bilinear projection for retaining discriminative information so as to determine the size of the deep architecture which enhances the success rate of vehicle detection. On-road experimental results demonstrate that the algorithm performs better than state-of-the-art vehicle detection algorithm in testing data sets.

scholarly journals A Multistep Framework for Vision Based Vehicle Detection

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Hai Wang ◽  
Yingfeng Cai
Keyword(s):  
Spatial Information ◽  
Vehicle Detection ◽  
Temporal Analysis ◽  
Detection Algorithm ◽  
Vehicle Classification ◽  
Depth Information ◽  
Data Sets ◽  
Deep Architecture ◽  
Critical Technology ◽  
Vehicle Active Safety

Vision based vehicle detection is a critical technology that plays an important role in not only vehicle active safety but also road video surveillance application. In this work, a multistep framework for vision based vehicle detection is proposed. In the first step, for vehicle candidate generation, a novel geometrical and coarse depth information based method is proposed. In the second step, for candidate verification, a deep architecture of deep belief network (DBN) for vehicle classification is trained. In the last step, a temporal analysis method based on the complexity and spatial information is used to further reduce miss and false detection. Experiments demonstrate that this framework is with high true positive (TP) rate as well as low false positive (FP) rate. On road experimental results demonstrate that the algorithm performs better than state-of-the-art vehicle detection algorithm in testing data sets.

Use of a Deep Belief Network for Small High-Level Abstraction Data Sets Using Artificial Intelligence with Rule Extraction

2018 ◽  
Vol 30 (12) ◽  
pp. 3309-3326 ◽  
Author(s):  
Yoichi Hayashi
Keyword(s):  
Rule Extraction ◽  
Deep Belief Network ◽  
Data Sets ◽  
Data Set ◽  
Simple Method ◽  
Learning Capability ◽  
Belief Network ◽  
Cancer Data ◽  
High Level ◽  
Very High

We describe a simple method to transfer from weights in deep neural networks (NNs) trained by a deep belief network (DBN) to weights in a backpropagation NN (BPNN) in the recursive-rule eXtraction (Re-RX) algorithm with J48graft (Re-RX with J48graft) and propose a new method to extract accurate and interpretable classification rules for rating category data sets. We apply this method to the Wisconsin Breast Cancer Data Set (WBCD), the Mammographic Mass Data Set, and the Dermatology Dataset, which are small, high-abstraction data sets with prior knowledge. After training these three data sets, our proposed rule extraction method was able to extract accurate and concise rules for deep NNs trained by a DBN. These results suggest that our proposed method could help fill the gap between the very high learning capability of DBNs and the very high interpretability of rule extraction algorithms such as Re-RX with J48graft.

scholarly journals Detection of Voltage Anomalies in Spacecraft Storage Batteries Based on a Deep Belief Network

Sensors ◽  
2019 ◽  
Vol 19 (21) ◽  
pp. 4702
Author(s):  
Li ◽  
Zhang ◽  
Liu
Keyword(s):  
Anomaly Detection ◽  
Power System ◽  
Detection Algorithm ◽  
Deep Belief Network ◽  
Normal Operation ◽  
Storage Battery ◽  
Belief Network ◽  
Orbit Satellite ◽  
Storage Batteries ◽  
Charge Discharge

For a spacecraft, its power system is vital to its normal operation and capacity to complete flight missions. The storage battery is an essential component of a power system. As a spacecraft spends more time in orbit and its storage battery undergoes charge/discharge cycles, the performance of its storage battery will gradually decline, resulting in abnormal multivariate correlations between the various parameters of the storage battery system. When these anomalies reach a certain level, battery failure will occur. Therefore, the detection of spacecraft storage battery anomalies in a timely and accurate fashion is of great importance to the in-orbit operation, maintenance and management of a spacecraft. Thus, in this study, based on storage battery-related telemetry parameter data (including charge/discharge currents, voltages, temperatures and times) downloaded from an in-orbit satellite, a voltage anomaly detection algorithm for spacecraft storage batteries based on a deep belief network (DBN) is proposed. By establishing a neural network (NN) model depicting the correlations between each of the variables of temperature, current, pressure and charge/discharge times and voltage, this algorithm supports the detection of anomalies in the state-of-health of a storage battery in a timely fashion. The proposed algorithm is subsequently applied to the storage battery of the aforementioned in-orbit satellite. The results show the following. The anomalies detected using the proposed algorithm are more reliable, effective and visual than those obtained using the conventional multivariate anomaly detection algorithms. Compared to the classic backpropagation NN-based algorithm, the DBN-based algorithm is notably advantageous in terms of the model training time and convergence.

Fault Detection Prediction Using a Deep Belief Network-Based Multi-Classifier in the Semiconductor Manufacturing Process

2019 ◽  
Vol 29 (08) ◽  
pp. 1125-1139
Author(s):  
Jae Kwon Kim ◽  
Jong Sik Lee ◽  
Young Shin Han
Keyword(s):  
Fault Detection ◽  
Manufacturing Process ◽  
Semiconductor Manufacturing ◽  
High Performance ◽  
Semiconductor Industry ◽  
Deep Belief Network ◽  
Second Phase ◽  
Data Sets ◽  
Belief Network ◽  
Imbalance Problem

The semiconductor manufacturing process is very complex, and it is the most important part of the semiconductor industry. In order to test whether or not wafers are functioning normally, a pass/fail test is conducted; however, time and cost needed for this testing increase as the number of chips increases. To address this, a machine learning technique is adopted and a high-performance classifier is needed to determine whether a pass/fail test is accurate or not. In this paper, a deep belief network (DBN)-based multi-classifier is proposed for fault detection prediction in the semiconductor manufacturing process. The proposed method consists of two phases: The first phase is a data pre-processing phase in which features required for semiconductor data sets are extracted and the imbalance problem is solved. The second phase is to configure the multi-DBN using selected features. A DBN classifier is created for each feature and, finally, fault detection prediction is performed. The proposed method showed excellent performance and can be used in the semiconductor manufacturing process efficiently.

A Parking Vehicle Detection Algorithm Using Magnetic Sensor

2013 ◽  
Vol 409-410 ◽  
pp. 1353-1356
Author(s):  
Zu Sheng Zhang ◽  
Hua Qiang Yuan ◽  
Liang Chen
Keyword(s):  
Vehicle Detection ◽  
Detection Algorithm ◽  
Magnetic Sensor ◽  
Sensor Nodes ◽  
One Year ◽  
Better Than

In this work, a parking vehicle detection algorithm using magnetic sensor is proposed. Eighty-two sensor nodes are deployed to evaluate the performance of the algorithm. By running the system for more than one year, we observe the vehicle detection accurate rate is better than 98%.

Sign in / Sign up

Export Citation Format

Share Document