A Comprehensive Survey of Deep Learning Models Based on Keras Framework

Chicho, Bahzad Taha; Sallow, Amira B.

doi:10.30880/jscdm.2021.02.02.005

Cited by 17 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Python script has a number of inbuilt libraries that support a variety of scientific computations and machine learning. The libraries include NumPy8, SciPy9, Matplotplib10, Keras and others that perform specific simulations, regression analysis and the determination of ordinary differential equations (Chicho & Sallow, 2021). These library options also enable time series forecasting.…”

Section: Python Programmingmentioning

confidence: 99%

Application of artificial neural networks for time series rainfall forecasting in the Loktak lift irrigation command area of Manipur, India

Yumkhaibam,

Kusre

2023

Irrigation and Drainage

View full text Add to dashboard Cite

The primary source of water for irrigation and other agricultural activities is rainfall. It has an immediate effect on crop growth and productivity. Forecasting this rainfall in advance allows farmers to effectively plan their cropping pattern. In recent years, forecasting rainfall has become very popular due to the availability of the latest computation techniques. Artificial neural networks (ANNs) are one such technique widely used for rainfall prediction by a number of researchers. These models are more reliable as they make better predictions because of their nonlinear data learning method. In the present study, an ANN model was developed to predict the annual, monsoon and postmonsoon season rainfall. The model was developed using 34 years of data from 1985 to 2018 in the command area of the Loktak Lift Irrigation Project in Manipur, India. The ANN model was trained using the rectified linear unit (ReLU) activation function. The 3‐year input model excelled in all seasons, with the best model achieving a 0.36 coefficient of determination (R2), 75.7 root mean square error, 0.60 correlation coefficient and 62.5 mean absolute error. These performance indicators were comparable with studies performed by other researchers. Thus, the model can be adopted for the study area.

show abstract

Section: Python Programmingmentioning

confidence: 99%

Application of artificial neural networks for time series rainfall forecasting in the Loktak lift irrigation command area of Manipur, India

Yumkhaibam,

Kusre

2023

Irrigation and Drainage

View full text Add to dashboard Cite

show abstract

“…Which is a popular machine learning software, which was written in Java and developed at the University of Waikato, New Zealand [6].An open source software provides tools for data preprocessing, implementation of several Machine Learning algorithms, and visualization tools so that you can develop machine learning techniques and apply them to real-world data mining problems. Keras has a wide variety of production deployment options and robust support for multiple Graphics Processing Unit and distributed training [8].  Simple -IT is simple but not simplistic.…”

Section: Tools Of Machine Learningmentioning

confidence: 99%

“… Flexible --Keras adopts the principle of progressive disclosure of complexity: simple workflows should be quick and easy.  Powerful --Keras provides industry-strength performance and scalability: it is used by organizations and companies including NASA, YouTube, or Waymo [8].…”

Section: Tools Of Machine Learningmentioning

confidence: 99%

Effects of Attributes Size on the Performance of Machine Learning Algorithms

Sinha,

Kushwaha

2023

eatp

View full text Add to dashboard Cite

Machine leaning is an emerging technology in research, it is extend as a great tool to explore and study of any area where data are collected in huge amount. This involves analyzing and interpreting patterns and structures in data to enable learning, reasoning, and decision-making without the need for direct human interaction. It use in many areas such as health care, finance, marketing etc. as a tool of research and development. Machine learning tools will enable you to play with the data, train your models, discover new methods, and create algorithms. This paper presents the study of some well known Machine learning algorithms and the effect of attribute size on their performance in the term of accuracy. Experimental result shows that performance changes for some algorithms. Accuracy of Naïve bayes, Logistic regression, SMO are decreased as the number of attributes increased, while Random forest and J48 performance are same in both the cases.

show abstract

“…Accuracy and precision, as well as recall and F1 score, are the metrics that were used in this study to evaluate the three classifiers [16], [17]. At the study's conclusion, a comparison of how well ResNet50, VGG16, and Inception performed will occur.…”

Section: Evaluation Parametersmentioning

confidence: 99%

Deep Learning Approach for Predicting Prostate Cancer from MRI Images

Chun,

Yousir,

Abdulameer

et al. 2022

JSCDM

View full text Add to dashboard Cite

According to medical data, prostate cancer has been one of the most lethal malignancies in recent years. Early detection of prostate cancer significantly influences the tumor's treatability. Image analysis software that operates using a machine learning or deep learning algorithm is one of the techniques utilized to aid in the early and rapid identification of prostate cancer. This paper evaluates the performance of three deep learning Convolutional neural network (CNN) algorithms in detecting prostate cancer. Using Python, three deep learning models, ResNet50, InceptionV3, and VGG16, are subsequently created on the Kaggle platform. These three models have been applied to various medical image diagnostic problems and have won several contests. This study used 620image samples from the Cancer Imaging Archive (TCIA) data source. Accuracy, f1 score, recall, and precision are used to evaluate the performance of the three models. The extracted test results indicate that the VGG16 achieves the highestlevel of accuracy at 95.56percent, followed by the ResNet50 at 86.67percent and the InceptionV3 at 85.56percent.

show abstract

A Comprehensive Survey of Deep Learning Models Based on Keras Framework

Cited by 17 publications

References 29 publications

Application of artificial neural networks for time series rainfall forecasting in the Loktak lift irrigation command area of Manipur, India

Application of artificial neural networks for time series rainfall forecasting in the Loktak lift irrigation command area of Manipur, India

Effects of Attributes Size on the Performance of Machine Learning Algorithms

Deep Learning Approach for Predicting Prostate Cancer from MRI Images

Contact Info

Product

Resources

About