Preferred Language
Articles
/
GheZh5IBVTCNdQwCRLMn
Improving Pre-trained CNN-LSTM Models for Image Captioning with Hyper-Parameter Optimization
...Show More Authors

The issue of image captioning, which comprises automatic text generation to understand an image’s visual information, has become feasible with the developments in object recognition and image classification. Deep learning has received much interest from the scientific community and can be very useful in real-world applications. The proposed image captioning approach involves the use of Convolution Neural Network (CNN) pre-trained models combined with Long Short Term Memory (LSTM) to generate image captions. The process includes two stages. The first stage entails training the CNN-LSTM models using baseline hyper-parameters and the second stage encompasses training CNN-LSTM models by optimizing and adjusting the hyper-parameters of the previous stage. Improvements include the use of a new activation function, regular parameter tuning, and an improved learning rate in the later stages of training. The experimental results on the flickr8k dataset showed a noticeable and satisfactory improvement in the second stage, where a clear increment was achieved in the evaluation metrics Bleu1-4, Meteor, and Rouge-L. This increment confirmed the effectiveness of the alterations and highlighted the importance of hyper-parameter tuning in improving the performance of CNN-LSTM models in image caption tasks.

Scopus Crossref
View Publication
Publication Date
Sat Jul 01 2017
Journal Name
Diyala Journal For Pure Science
Correlated Hierarchical Autoregressive Models Image Compression
...Show More Authors

View Publication
Crossref
Publication Date
Tue Nov 01 2022
Journal Name
2022 International Conference On Data Science And Intelligent Computing (icdsic)
An improved Bi-LSTM performance using Dt-WE for implicit aspect extraction
...Show More Authors

In aspect-based sentiment analysis ABSA, implicit aspects extraction is a fine-grained task aim for extracting the hidden aspect in the in-context meaning of the online reviews. Previous methods have shown that handcrafted rules interpolated in neural network architecture are a promising method for this task. In this work, we reduced the needs for the crafted rules that wastefully must be articulated for the new training domains or text data, instead proposing a new architecture relied on the multi-label neural learning. The key idea is to attain the semantic regularities of the explicit and implicit aspects using vectors of word embeddings and interpolate that as a front layer in the Bidirectional Long Short-Term Memory Bi-LSTM. First, we

... Show More
View Publication Preview PDF
Scopus (4)
Crossref (2)
Scopus Crossref
Publication Date
Fri Apr 20 2018
Journal Name
Iaes International Journal Of Artificial Intelligence (ij-ai)
Optimization of Digital Histopathology Image Quality
...Show More Authors

One of the biomedical image problems is the appearance of the bubbles in the slide that could occur when air passes through the slide during the preparation process. These bubbles may complicate the process of analysing the histopathological images. The objective of this study is to remove the bubble noise from the histopathology images, and then predict the tissues that underlie it using the fuzzy controller in cases of remote pathological diagnosis. Fuzzy logic uses the linguistic definition to recognize the relationship between the input and the activity, rather than using difficult numerical equation. Mainly there are five parts, starting with accepting the image, passing through removing the bubbles, and ending with predict the tissues

... Show More
View Publication Preview PDF
Scopus (3)
Crossref (1)
Scopus Crossref
Publication Date
Sat Jan 01 2022
Journal Name
The 2nd Universitas Lampung International Conference On Science, Technology, And Environment (ulicoste) 2021
A comparison between IRI-2016 and ASAPS models for predicting foF2 ionospheric parameter over Baghdad city
...Show More Authors

View Publication
Scopus (1)
Scopus Crossref
Publication Date
Wed Mar 10 2021
Journal Name
Baghdad Science Journal
Improving Fractal Image Compression Scheme through Quantization Operation
...Show More Authors

We explore the transform coefficients of fractal and exploit new method to improve the compression capabilities of these schemes. In most of the standard encoder/ decoder systems the quantization/ de-quantization managed as a separate step, here we introduce new way (method) to work (managed) simultaneously. Additional compression is achieved by this method with high image quality as you will see later.

View Publication Preview PDF
Crossref
Publication Date
Thu Nov 29 2018
Journal Name
Iraqi Journal Of Science
Improving Extractive Multi-Document Text Summarization Through Multi-Objective Optimization
...Show More Authors

Multi-document summarization is an optimization problem demanding optimization of more than one objective function simultaneously. The proposed work regards balancing of the two significant objectives: content coverage and diversity when generating summaries from a collection of text documents.

     Any automatic text summarization system has the challenge of producing high quality summary. Despite the existing efforts on designing and evaluating the performance of many text summarization techniques, their formulations lack the introduction of any model that can give an explicit representation of – coverage and diversity – the two contradictory semantics of any summary. In this work, the design of

... Show More
View Publication Preview PDF
Publication Date
Thu Feb 01 2024
Journal Name
Baghdad Science Journal
Improving the efficiency and security of passport control processes at airports by using the R-CNN object detection model
...Show More Authors

The use of real-time machine learning to optimize passport control procedures at airports can greatly improve both the efficiency and security of the processes. To automate and optimize these procedures, AI algorithms such as character recognition, facial recognition, predictive algorithms and automatic data processing can be implemented. The proposed method is to use the R-CNN object detection model to detect passport objects in real-time images collected by passport control cameras. This paper describes the step-by-step process of the proposed approach, which includes pre-processing, training and testing the R-CNN model, integrating it into the passport control system, and evaluating its accuracy and speed for efficient passenger flow

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Crossref
Publication Date
Wed Mar 01 2023
Journal Name
Journal Of Engineering
Stiffness Characteristics of Pile Models for Cement Improving Sandy Soil by Low-Pressure Injection Laboratory Setup
...Show More Authors

Soil improvement has developed as a realistic solution for enhancing soil properties so that structures can be constructed to meet project engineering requirements due to the limited availability of construction land in urban centers. The jet grouting method for soil improvement is a novel geotechnical alternative for problematic soils for which conventional foundation designs cannot provide acceptable and lasting solutions. The paper's methodology was based on constructing pile models using a low-pressure injection laboratory setup built and made locally to simulate the operation of field equipment. The setup design was based on previous research that systematically conducted unconfined compression testing (U.C.Ts.). Th

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Dec 23 2020
Journal Name
Iraqi Journal For Electrical And Electronic Engineering
Heuristic and Meta-Heuristic Optimization Models for Task Scheduling in Cloud-Fog Systems: A Review
...Show More Authors

Nowadays, cloud computing has attracted the attention of large companies due to its high potential, flexibility, and profitability in providing multi-sources of hardware and software to serve the connected users. Given the scale of modern data centers and the dynamic nature of their resource provisioning, we need effective scheduling techniques to manage these resources while satisfying both the cloud providers and cloud users goals. Task scheduling in cloud computing is considered as NP-hard problem which cannot be easily solved by classical optimization methods. Thus, both heuristic and meta-heuristic techniques have been utilized to provide optimal or near-optimal solutions within an acceptable time frame for such problems. In th

... Show More
View Publication
Crossref (6)
Crossref
Publication Date
Sat Jun 27 2020
Journal Name
Iraqi Journal Of Science
Lower and Upper Bounds for Hyper-Zagreb Index of Graphs
...Show More Authors

The topological indices are functions on the graph that do not depend on the labeling of their vertices. They are used by chemists for studying the properties of chemical compounds.  Let  be a simple connected graph. The Hyper-Zagreb index of the graph ,  is defined as  ,where  and  are the degrees of vertex  and , respectively. In this paper, we study the Hyper-Zagreb index and give upper and lower bounds for .

View Publication Preview PDF
Scopus (3)
Scopus Crossref