Differentiating between military sounds can be quite tasking with high false detection rate. These sounds can either be impulse sounds (sounds released from the military weapons) or non-impulse sounds (sound released ...
详细信息
ISBN:
(纸本)9783030243081
Differentiating between military sounds can be quite tasking with high false detection rate. These sounds can either be impulse sounds (sounds released from the military weapons) or non-impulse sounds (sound released from other sources) thus causing public disturbance and unnecessary panic. This paper utilizes Deep Convolutional Neural Network (DCNN) classifier to detect military impulse and non-impulse sounds and also incorporates adam algorithm for optimal classification. DCNN was utilized in this study based on its network embedded multiple hidden layers (non-linear) which can learn the very complicated relationship between the input data and require output. The dataset used in this study consist of six sound types with a total number of 37,464 datasets which was partitioned into training (67%) and testing (33%). The performance of the proposed classifier was evaluated based on the following metrics: True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), Precision, Matthews Correlation Coefficient (MCC), and Accuracy. The experimental result shows that DCNN classifier gave an optimal accuracy for the Machine gun, Wind, Thunder, Blast, Vehicle, and Aircraft sounds types as 97.43%, 96.98%, 95.16%, 95.13%, 88.83%, and 87% respectively. The average classification error rate for the six sound types was 6.57% which signifies that DCNN is a promising classifier.
The Broad Learning System (BLS) has recently been proposed as an effective and useful method for pattern recognition. It overcomes the shortcomings of deep neural networks that are both time consuming and hardware dep...
详细信息
ISBN:
(纸本)9781728136608
The Broad Learning System (BLS) has recently been proposed as an effective and useful method for pattern recognition. It overcomes the shortcomings of deep neural networks that are both time consuming and hardware dependent. BLS is a lightweight network structure. Although its advantages in speed and flexibility arc obvious, there is a still a gap between its accuracy in image recognition and that of state-of-art approaches. We propose a BLS-based model that combines CNN and adam algorithm. At first, we build a BLS-based classifier, and then we build a CNN-based feature extraction. After that, we take features extracted as inputs to the classifier. Feature extraction through convolution and pooling operations can effectively preserve key features of the image. We use adam algorithm to update the weights of the feature extraction. By retaining key features and removing factors that affect image recognition, it helps to improve the accuracy of the classification results. Therefore, through the above operations, the speed and accuracy of our proposed lightweight network structure haves been improved and reflected in the dataset of the MNIST and Cat or Dog for Kaggle competitions. We can choose different convolution layers, pooling layers and optimization algorithms according to the different sized data sets.
Face recognition is a widely utilized biometric method due to its natural and non-intrusive approach. Recently, deep learning networks using Triplet Loss have become a common framework for person identification and ve...
详细信息
Face recognition is a widely utilized biometric method due to its natural and non-intrusive approach. Recently, deep learning networks using Triplet Loss have become a common framework for person identification and verification. In this paper, we present a new method on how to select appropriate hard-negatives for training using Triplet Loss. We show that, by incorporating pairs which would otherwise have been discarded yields better accuracy and performance. We also applied Adaptive Moment Estimation algorithm to mitigate the risk of early convergence due to the additional hard-negative pairs. In LFW verification benchmark, we managed to achieve an accuracy of 0.955 and AUC of 0.989 as opposed to 0.929 and 0.973 in the original OpenFace.
BP neural network and rough set theory play an important role in the field of *** view of the present situation of customer churn in logistics industry,this paper combines rough set and BP neural network to forecast c...
详细信息
ISBN:
(纸本)9781510876996
BP neural network and rough set theory play an important role in the field of *** view of the present situation of customer churn in logistics industry,this paper combines rough set and BP neural network to forecast customer attrition behavior in logistics ***,using rough sets to extract rules from normal and abnormal customers to distinguish customer classes in logistics *** processing of information entropy of extracted logistics customer attributes based on rough sets being good at handling discrete ***,according to the strong mobility of logistics customers,adam algorithm is introduced to build an adaptive BP neural network training *** model proposed in this paper is more suitable for real-time data *** experiment proves that the method is feasible and efficient.
暂无评论