@nahrainuniv.edu.iq
Al-Nahrain University
Scopus Publications
Scholar Citations
Scholar h-index
Hind Khalid
EDP Sciences
This study aims to develop an annotation and image annotation system using the Fashion MNIST dataset, which consists of 70,000 grayscale images of ten clothing categories. The system uses a long short-term memory (LSTM) network to generate captions and a convolutional neural network (CNN) to extract image features. Performance evaluation metrics such as Precision, Recall, F1 score, BLEU score, METEOR score, CIDEr score, and ROUGE-L score are used where the accuracy of each clothing category is calculated to evaluate the performance of the model across different categories. Visual analysis of the generated captions is performed to gain insight into the effectiveness of the model and potential areas for improvement. The results indicate the model's success in classifying clothing items, as evidenced by its high accuracy on the test set. The qualitative study reveals the model's ability to identify different types of clothing by providing relevant captions, where the feature representation layer (normalization) plays a crucial role in transforming the detected features. to a flattened row which is then passed to a fully connected layer to learn the relationships and make final decisions with the output layer using a softmax activation function to assign probabilities to each image class, with the class with the highest probability selected as the predicted image class.
H. Khalid
Universidad Nacional Autonoma de Mexico
Recent developments in machine vision have opened up a wide range of applications, and farming is no exception. Deep learning (DL) has a wide range of applications because of its capacity to extract robust features from photos. Shape, color, and feel of many fruit species make it difficult to discover and classify fruits. When examining the effects of artificial intelligence on fruit identification and classification, we noted that, up until 2018, the majority of approaches relied on traditional machine learning (ML) techniques, while just a few ways took use of DL techniques for recognizing fruits and categorization. In this post, we thoroughly covered the datasets that many academics utilized, the useful descriptors, the application of model, and the difficulties of utilizing DL to identify and classify fruits. Finally, we compiled the outcomes of various DL techniques used in earlier research to identify and categorize fruits. This work examines the use of models based on DL for fruit categorization and recognition in recent studies. In order to make it simpler for beginning agricultural researchers to comprehend the importance of ML in the agricultural domain, we have developed a DL model for apple categorization using the well-known dataset "Fruit 360" starting scratch.
Hind Khalid
Journal of Physics: Conference Series IOP Publishing
The aim of this research is to show what benefits the use of neural networks in forecasting processes can bring, among its development through out the years considering different kinds of mathematical methods. The software applications that have been developed recently for forecasting processes are neural and AI-based. Data entries from previous months are used in mathematical methods to calculate and predict sales in a company. By the use of these neural and AI-based processes, predictions of whether company sales will go up or down the next month can be made. This research will help to better understand the process behind these predictions and how the developments of neural networks come into place.