The convolutional neural networks (CNN) are among the most utilized neural networks in various applications, including deep learning. In recent years, the continuing extension of CNN into increasingly complicated domains has made its training process more difficult. Thus, researchers adopted optimized hybrid algorithms to address this problem. In this work, a novel chaotic black hole algorithm-based approach was created for the training of CNN to optimize its performance via avoidance of entrapment in the local minima. The logistic chaotic map was used to initialize the population instead of using the uniform distribution. The proposed training algorithm was developed based on a specific benchmark problem for optical character recog

LK Abood, RA Ali, M Maliki, International Journal of Science and Research, 2015 - Cited by 2

Ultrasound has been used as a diagnostic modality for many intraocular diseases, due its safety, low cost, real time and wide availability. Unfortunately, ultrasound images suffer from speckle artifact that are tissue dependent. In this work, we will offer a method to reduce speckle noise and improve ultrasound image to raise the human diagnostic performance. This method combined undecimated wavelet transform with a wavelet coefficient mapping function: where UDWT used to eliminate the noise and a wavelet coefficient mapping function used to enhance the contrast of denoised images obtained from the first component. This methods can be used not only as a means for improving visual quality of medical images but also as a preprocessing

Alpha shape theory for 3D visualization and volumetric measurement of brain tumor progression using magnetic resonance images

Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97–100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with

      The Matching and Mosaic of the satellite imagery play an essential role in many remote sensing and image processing projects. These techniques must be required in a particular step in the project, such as remotely change detection applications and the study of large regions of interest. The matching and mosaic methods depend on many image parameters such as pixel values in the two or more images, projection system associated with the header files, and spatial resolutions, where many of these methods construct the matching and mosaic manually. In this research, georeference techniques were used to overcome the image matching task in semi automotive method. The decision about the quality of the technique can be considered i

Cryptocurrency became an important participant on the financial market as it attracts large investments and interests. With this vibrant setting, the proposed cryptocurrency price prediction tool stands as a pivotal element providing direction to both enthusiasts and investors in a market that presents itself grounded on numerous complexities of digital currency. Employing feature selection enchantment and dynamic trio of ARIMA, LSTM, Linear Regression techniques the tool creates a mosaic for users to analyze data using artificial intelligence towards forecasts in real-time crypto universe. While users navigate the algorithmic labyrinth, they are offered a vast and glittering selection of high-quality cryptocurrencies to select. The

With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor se