AUDD: Audio Urdu Digits Dataset for Automatic Audio Urdu Digit Recognition

Chandio, Aisha; Shen, Yao; Bendechache, Malika; Inayat, Irum; Kumar, Tipparti Anil

doi:10.3390/app11198842

Cited by 48 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For effective learning and implementation, a CNN model needs to be trained with a large amount of the training data [18,33]. e deep learningbased approaches need to be trained on large training datasets for avoiding overfitting and to maximize learning.…”

Section: Data Augmentationmentioning

confidence: 99%

Recognizing the Damaged Surface Parts of Cars in the Real Scene Using a Deep Learning Framework

Parhizkar

Amirfakhrian

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Automatically recognizing the damaged surface parts of cars can noticeably diminish the cost of processing premium assertion that leads to providing contentment for vehicle users. This recognition task can be conducted using some machine learning (ML) strategies. Deep learning (DL) models as subsets of ML have indicated remarkable potential in object detection and recognition tasks. In this study, an automated recognition of the damaged surface parts of cars in the real scene is suggested that is based on a two-path convolutional neural network (CNN). Our strategy utilizes a ResNet-50 at the beginning of each route to explore low-level features efficiently. Moreover, we proposed new mReLU and inception blocks in each route that are responsible for extracting high-level visual features. The experimental results proved the suggested model obtained high performance in comparison to some state-of-the-art frameworks.

show abstract

Section: Data Augmentationmentioning

confidence: 99%

Recognizing the Damaged Surface Parts of Cars in the Real Scene Using a Deep Learning Framework

Parhizkar

Amirfakhrian

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Moreover, in order to avoid memorization, a dropout of 0.15 is used. For increasing the training samples, two augmentation strategies are utilized including random rotations and random Gaussian noise [26,32,58]. The utilized parameters for training the CNN model are shown in Table 1.…”

Section: Our Deep Learning Model (22)mentioning

confidence: 99%

Recognizing and segmenting particles inside the respiratory system using texture descriptor and deep learning approaches

Khadem¹,

Mohammadi²,

Soltani³

2022

J Clin Images Med Case Rep

View full text Add to dashboard Cite

The study of aerosol deposition and bronchial tube flows in the human respiratory system can assistance improve an understanding of the damaging or beneficial effects of the inhalation of lung aerosols. In this study, we propose a strategy for segmenting the decomposition of particles inside the respiratory system. Firstly, a texture descriptor method is used to represent more unique features for obtaining the border of each particle more accurately. Next, the original image and the encoded image are applied to a Convolutional Neural Network model to generate the edge map of the input image. Lastly, a circle fitting approach to compare each object with a lot of potential circles is employed to find the best match and recognize the object. A comparison of the results obtained in this study with some texture descriptor approaches is demonstrated the good performance of our model.

show abstract

“…Nevertheless, they proved to have poor performance especially when the network is large like CNN since the learning rate needs to be manually tuned in SGD. This significantly increases the training time for large-scale datasets [ 26 , 27 ]. To overcome this obstacle and improve the efficiency of adaptive, new variants of adaptive gradient methods are proposed such as Nostalgic Adam [ 28 ], which place bigger weights on the past gradient compared to the recent gradient, or YOGI [ 29 ], which increases in effective learning rate to achieve better convergence.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Effectiveness of Shuffled Frog-Leaping Optimizer in Training a Convolution Neural Network

Saadi

Sarshar

Sadeghi

et al. 2022

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

One of the leading algorithms and architectures in deep learning is Convolution Neural Network (CNN). It represents a unique method for image processing, object detection, and classification. CNN has shown to be an efficient approach in the machine learning and computer vision fields. CNN is composed of several filters accompanied by nonlinear functions and pooling layers. It enforces limitations on the weights and interconnections of the neural network to create a good structure for processing spatial and temporal distributed data. A CNN can restrain the numbering of free parameters of the network through its weight-sharing property. However, the training of CNNs is a challenging approach. Some optimization techniques have been recently employed to optimize CNN’s weight and biases such as Ant Colony Optimization, Genetic, Harmony Search, and Simulated Annealing. This paper employs the well-known nature-inspired algorithm called Shuffled Frog-Leaping Algorithm (SFLA) for training a classical CNN structure (LeNet-5), which has not been experienced before. The training method is investigated by employing four different datasets. To verify the study, the results are compared with some of the most famous evolutionary trainers: Whale Optimization Algorithm (WO), Bacteria Swarm Foraging Optimization (BFSO), and Ant Colony Optimization (ACO). The outcomes demonstrate that the SFL technique considerably improves the performance of the original LeNet-5 although using this algorithm slightly increases the training computation time. The results also demonstrate that the suggested algorithm presents high accuracy in classification and approximation in its mechanism.

show abstract

AUDD: Audio Urdu Digits Dataset for Automatic Audio Urdu Digit Recognition

Cited by 48 publications

References 28 publications

Recognizing the Damaged Surface Parts of Cars in the Real Scene Using a Deep Learning Framework

Recognizing the Damaged Surface Parts of Cars in the Real Scene Using a Deep Learning Framework

Recognizing and segmenting particles inside the respiratory system using texture descriptor and deep learning approaches

Investigation of Effectiveness of Shuffled Frog-Leaping Optimizer in Training a Convolution Neural Network

Contact Info

Product

Resources

About