Deep Learning Algorithms and Applications in Computer Vision

Shetty, Savita; Siddiqa, Ayesha

doi:10.26438/ijcse/v7i7.195201

Cited by 11 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recurrent Neural Networks (RNN), Deep Belief Networks (DBN), Convolutional Neural Networks (CNN), and Deep Neural Networks (DNN) are the primary algorithms used in deep learning. Each of these algorithms is applied for various analyses according to the needs and performance of different types of data (13). All the methods discussed are interrelated, where DL is a technique from ANN, while ANN is a technique from ML, and the last one is that AI is the parent of all because ML is a technique in AI (14).…”

Section: Methodsmentioning

confidence: 99%

Makassar City Air Pollution Forecast in 2045

Jusri,

Jamil,

Barkey

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Air pollution is a problem for all countries in the world, especially for urban areas, because most sources of air pollution are in urban areas. In 2019, it was predicted that ambient air pollution from PM2.5 caused 4.2 million premature deaths globally. It contributes to cancer, respiratory, and cardiovascular problems. Makassar is the most populous city in South Sulawesi Province, with a population of 1,427,619 in 2021. The number of motorized vehicles in 2021 is 1,740,793 units and 1,113 industries. With these conditions, Makassar City has a high potential for air pollution. This research aims to forecast the air pollution level of Makassar City in 2045. The forecasting results can be a reference in developing an air pollution control plan in Makassar City. The forecasting model used is LSTM which is the development of RNN architecture. The results of air pollution forecasting are displayed in the form of an air pollution standard index (ISPU) for easy understanding by the general public. Based on the forecasting results in 2045, the level of air pollution in Makassar City is in the moderate and unhealthy categories. Despite still being dominated by the moderate category, it should be a concern that air quality is no longer in the good category.

show abstract

Section: Methodsmentioning

confidence: 99%

Makassar City Air Pollution Forecast in 2045

Jusri,

Jamil,

Barkey

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…There are different training algorithms available in the literature for training a neural network and updating their weights and biases [27] . Various performance parameters of training of NN are available in the literature, like the negative log-likelihood loss (NLL) function, cross-entropy function, and mean square error (MSE) [22,28]. The MSE is the default performance parameter and is represented as…”

Section: Training Algorithmsmentioning

confidence: 99%

Performance analysis of various training algorithms of deep learning based controller

2023

View full text Add to dashboard Cite

Advances in artificial neural networks (ANN), specifically deep learning (DL), have widened the application domain of process control. DL algorithms and models have become quite common these days. The training algorithm is the most important part of an ANN that affects the performance of the controller. Training algorithms optimize the weights and biases of the ANN according to the input-output patterns. In this paper, the performance of different training algorithms was evaluated, analysed, and compared in a feed-forward backpropagation architecture. The training algorithms were simulated on MATLAB R2021b with license number 1075356. Training data were generated using two benchmark problems of the process control system. The performance, gradient, training error, validation error, testing error, and regression of the different training algorithms were obtained and analysed. The data shows that the Levenberg-Marquardt (LM) algorithm produced the best validation performance with a value of 2.669*10−14 at 2000 epochs, while ‘traingd’ and ‘traingdm’ algorithms did not improve beyond their initial values. The LM algorithm tends to produce better results than other algorithms. These results indicate that the LM backpropagation best suits these types of benchmark problems. The results also suggest that the choice of training algorithm can significantly impact the performance of a neural network.

show abstract

“…Different pooling techniques are available, usually based on the requirement. The most commonly used one is max pooling, which only considers the highest concentrated element of the obtained feature map [21]. Sub-sampling is frequently achieved using max/mean pooling or local averaging filters [3].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…Sub-sampling is frequently achieved using max/mean pooling or local averaging filters [3]. After flattening the generated feature map, the 1D array is sent into a fully connected network [21]. The final layer of CNN handles the actual classifications.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning for Arabic phonemes recognition using electrolarynx speech

Ameen

Kadhim²

2023

IJECE

View full text Add to dashboard Cite

<p><span lang="EN-US">Automatic speech recognition system is one of the essential ways of interaction with machines. Interests in speech based intelligent systems have grown in the past few decades. Therefore, there is a need to develop more efficient methods for human speech recognition to ensure the reliability of communication between individuals and machines. This paper is concerned with Arabic phoneme recognition of electrolarynx device. Electrolarynx is a device used by cancer patients having vocal laryngeal cords removed. Speech recognition here is considered to find the preferred machine learning model that can classify phonemes produced by electrolarynx device. The phonemes recognition employs different machine learning schemes, including convolutional neural network, recurrent neural network, artificial neural network (ANN), random forest, extreme gradient boosting (XGBoost), and long short-term memory. Modern standard Arabic is utilized for testing and training phases of the recognition system. The dataset covers both an ordinary speech and electrolarynx device speech recorded by the same person. Mel frequency cepstral coefficients are considered as speech features. The results show that the ANN machine learning method outperformed other methods with an accuracy rate of 75%, a precision value of 77%, and a phoneme error rate (PER) of 21.85%.</span></p>

show abstract

Deep Learning Algorithms and Applications in Computer Vision

Cited by 11 publications

References 0 publications

Makassar City Air Pollution Forecast in 2045

Makassar City Air Pollution Forecast in 2045

Performance analysis of various training algorithms of deep learning based controller

Machine learning for Arabic phonemes recognition using electrolarynx speech

Contact Info

Product

Resources

About