Qanita Bani Baker | Utah State University (original) (raw)

Papers by Qanita Bani Baker

Open House International, 2021

Purpose Virtual reality (VR) technology invaded various domains including architecture practice a... more Purpose Virtual reality (VR) technology invaded various domains including architecture practice and education. Despite its high applications in architecture design education, VR has a high potential to be used in architectural history courses as well. This paper aims to examine the effect of using VR technology on the students’ learning abilities of history of architecture. Design/methodology/approach The experimental approach was used. Two experiments were designed by creating virtual environments for two selected architectural examples from the Modern Architecture course. The participants who were students of Modern Architecture class had to complete two questionnaires, one for each example. The first one was based on Bloom’s taxonomy, and the other was prepared to test the participants’ analytical and critical skills. Besides, participants had to fill out satisfaction and ease-of-use survey on a five-step Likert scale. Findings Participants in the VR condition achieved better gra...

2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA)

2021 12th International Conference on Information and Communication Systems (ICICS)

Lung cancer is one of the most commonly diagnosed cancer. Most studies found that lung cancer pat... more Lung cancer is one of the most commonly diagnosed cancer. Most studies found that lung cancer patients have a survival time up to 5 years after the cancer is found. An accurate prognosis is the most critical aspect of a clinical decision-making process for patients. predicting patients’ survival time helps healthcare professionals to make treatment recommendations based on the prediction. In this paper, we used various deep learning methods to predict the survival time of Non-Small Cell Lung Cancer (NSCLC) patients in days which has been evaluated on clinical and radiomics dataset. The dataset was extracted from computerized tomography (CT) images that contain data for 300 patients. The concordance index (C-index) was used to evaluate the models. We applied several deep learning approaches and the best accuracy gained is 70.05% on the OWKIN task using Multilayer Perceptron (MLP) which outperforms the baseline model provided by the OWKIN task organizers

International Journal of Electrical and Computer Engineering (IJECE), 2021

This article studies and analyzes the use of 3D models, built from magnetic resonance imaging (MR... more This article studies and analyzes the use of 3D models, built from magnetic resonance imaging (MRI) axial scans of the lumbar intervertebral disk, that are needed for the diagnosis of disk herniation. We study the possibility of assisting radiologists and orthopedists and increasing their quality of experience (QoE) during the diagnosis process. The main aim is to build a 3D model for the desired area of interest and ask the specialists to consider the 3D models in the diagnosis process instead of considering multiple axial MRI scans. We further propose an automated framework to diagnose the lumber disk herniation using the constructed 3D models. We evaluate the effectiveness of increasing the specialists QoE by conducting a questionnaire on 14 specialists with different experiences ranging from residents to consultants. We then evaluate the effectiveness of the automated diagnosis framework by training it with a set of 83 cases and then testing it on an unseen test set. The results...

I am very grateful to Dr. Al Forsyth for his support and helpful suggestions for this dissertatio... more I am very grateful to Dr. Al Forsyth for his support and helpful suggestions for this dissertation writing.

2021 Eighth International Conference on Social Network Analysis, Management and Security (SNAMS), 2021

Coronavirus, known as COVID-19, rapidly spread on a wide scale in a short time consequently. Worl... more Coronavirus, known as COVID-19, rapidly spread on a wide scale in a short time consequently. World Health Organization (WHO) classified it as a global pandemic. Social networks news becomes a valuable resource for massive amounts of data and news about the epidemic in which news is deliberating every day. Twitter is one of these networks which is a popular platform that contains rich information and currently it repre-sents a rich resource of data about COVID-19. In this research, we study and analyze the spreading of the COVID-19 epidemic based on the location and dates using datasets from Twitter. Moreover, the study has done by performing sentiment analysis and making a correlation study between confirmed cases in a set of countries and the sentiment's polarity value including negative and positive as well as a correlation between the number of confirmed cases and number of tweets per country. Also, we have experimented with several machine learning classifiers including Naive base, Support Vector Machine, and Logistic Regression as well as RoBERTa model to predict the sentiment analysis on the dataset. The experimental results show that Logistic Regression outperforms other classifiers with an accuracy of 0.86%, thus, machine learning techniques could be used to study the sentiment of tweets which gives reasonable results.

2021 12th International Conference on Information and Communication Systems (ICICS), 2021

With the increase in life-threatening viral diseases, the need for extensive research on its caus... more With the increase in life-threatening viral diseases, the need for extensive research on its causes, recovery, and methods of prevention becomes crucial. Some of these diseases are dangerous and sometimes they might cause death. Dengue Fever remains one of the important public health issues expanded several areas all around the world. Dengue Fever spread could be affected by several factors such as climate conditions. In this paper, we analyze a weather-related dataset to predict the number of illness cases per week in the cities of San Juan and Iquitos by using several machine learning regression algorithms. To achieve this, we utilized and compared different machine learning regression techniques, the performance is evaluated using the Mean Absolute Error (MAE). As a result, the Poisson Regression Model achieved the best ratios and the lowest mean absolute error ratio of 25.6%.

2018 9th International Conference on Information and Communication Systems (ICICS), 2018

Bioinformatics is a growing field that attracts many researchers and continues to prove its value... more Bioinformatics is a growing field that attracts many researchers and continues to prove its value and significance. Since the early days of discovering genomic martial and using it to identify new life forms, sequence alignment applications have become important in enabling discoveries of important biological or medical benefits. Finding similarities, or even relations between sequences, is a demanding process that requires time and high cost. However, nowadays there are plenty of algorithms that are used to find similarity and/or differences between sequences. Many of these algorithms still suffer from performance issues, such as slow performance and poor scalability. Therefore, parallelization is widely used to address these issues. In this paper, we utilize a multi-threading parallelism technique coupled with a block alignment idea in order to improve the sequence alignment performance. The experiments show that the proposed implementation outperforms the sequential implementation by 4.9 times for sequences of lengths ranging between 1024 and 8192.

2017 8th International Conference on Information and Communication Systems (ICICS), 2017

White blood cell (WBC) segmentation is one of the important topics in the medical image processin... more White blood cell (WBC) segmentation is one of the important topics in the medical image processing field. Several researchers used K-means clustering approach to segment WBC from blood smear microscopic images. In this paper, we use the parallelism capabilities of the Graphics Processing Units (GPUs) to accelerate the segmentation of WBC from microscopic images. We implement the K-means algorithm and the preprocess steps for WBC image segmentation in CUDA programming to take the advantages of large number of cores in GPUs. We systematically implement and evaluate the performance of WBC segmentation operations on CPU, GPUs, and CPU-GPU hybrid systems. In this work, we gained about 3X faster performance than sequential implementation achieved without affecting WBC segmentation accuracy.

The transition in breast cancer from ductal carcinoma in situ to invasive ductal carcinoma marks ... more The transition in breast cancer from ductal carcinoma in situ to invasive ductal carcinoma marks a significant drop in patient survival and is one of the leading causes of death in women. Tumor initiation, growth, and metastasis are primarily driven by multiple biochemical and biomechanical interactions among the epithelia, tumor cells, diffusible signals, and stromal components such as fibroblasts, myofibroblasts and extracellular matrix in the ductal microenvironments. Understanding how the interplay among these components drives the dynamics of metastasis and invasion may lead to new therapeutic approaches to breast cancer. We introduced a 3D multicellular agent-based model of DCIS growth and invasion that includes ductal, stromal and tumor cell types acting along with microenvironmental components such as matrix metalloproteinases (MMP), Lysyl oxidase(LOX), nutrients, TGF\u27 and extracellular matrix (ECM) protein assemblies. We are investigating a wide range of parameters and assumptions in our model that lead to change in the model outcomes. The model explicitly determines mechanical tensional and compressive forces within the developing tissue

2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA), 2018

Breast cancer detection and classification using histological images play a critical role in the ... more Breast cancer detection and classification using histological images play a critical role in the breast cancer diagnosis process. This paper presents a framework for autodetection and classification of breast cancer from microscopic histological images. The images are classified into benign or malignant. The proposed framework involves several steps which include image enhancement, image segmentation, features extraction, and images classification. The proposed framework utilizes a novel combination of K-means clustering and watershed algorithms in the segmentation step. We used K-means clustering to produce an initial segmented image and then we applied the watershed segmentation algorithm. Classification results show that the proposed method effectively detect and classify breast cancer from histological image with accuracy of 70.7% using a proposed Rule-Based classifier and 86.5% using a Decision Tree classifier.

2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), 2019

Protein-protein interactions can be modeled as networks. The huge amount of produced Protein-Prot... more Protein-protein interactions can be modeled as networks. The huge amount of produced Protein-Protein Interaction (PPI)data has many applications in biological studies. These studies improved human knowledge in the life process and diseases. One of these studies is PPI network alignment, which finds the similarity between PPI networks as a biological similarity. Aligning these networks is important to investigate evolutionary pathways or protein complexes. The main challenge of all global PPI network alignment is to improve both accuracy and efficiency. In this research, the accuracy and efficiency of global PPI network alignment are improved by using the genetic algorithm instead of the greedy algorithm and applied in HubAlign framework. The performance of the proposed method is compared with HubAlign based on the total execution time for the alignment process and the correctness of the results of the aligned networks. The new approach enhanced the overall accuracy and reduce execution time compared to the HubAlign approach.

2021 12th International Conference on Information and Communication Systems (ICICS), 2021

Breast cancer classification and detection using histopathological images is considered a difficu... more Breast cancer classification and detection using histopathological images is considered a difficult process due to the complexity of the characteristics of histopathology images. This paper presents an automated system for the classification and detection of breast cancer from microscopic histological images where the images are classified into benign, in situ, invasive, and normal. The proposed approach involves several steps which are image preprocessing (Enhancement), image segmentation, feature extraction, feature selection, and finally image classification. The proposed approach utilizes and compares two segmentation methods which are clustering and Global thresholding using Otsu’s method. Initially, images are segmented using K-means and Global thresholding methods. Then, features (morphological and texture) are extracted from the images for the two methods. Moreover, feature selection is done by using Principal Component Analysis (PCA). Finally, K-means and Global thresholding methods are compared in the classification process by using different classifiers. The results show better performance for the Global thresholding.

International Journal of Electrical and Computer Engineering (IJECE), 2020

This paper studies the problem of clinical MRI analysis in the field of lumbar intervertebral dis... more This paper studies the problem of clinical MRI analysis in the field of lumbar intervertebral disk herniation diagnosis. It discusses the possibility of assisting radiologists in reading the patients MRI images by constructing a 3D model for the region of interest using simple computer vision methods. We use axial MRI slices of the lumbar area. The proposed framework works with a very small number of MRI slices and goes through three main stages. Namely, the region of interest extraction and enhancement, inter-slice interpolation, and 3D model construction. We use the Marching Cubes algorithm to construct the 3D model of the the region of interest. The validation of our 3D models is based on a radiologist’s analysis of the models. We tested the proposed 3D model construction on 83 cases and We have a 95% accuracy according to the radiologist evaluation. This study shows that 3D model construction can greatly ease the task of the radiologist which enhances the working experience. Thi...

Concurrency and Computation: Practice and Experience, 2019

White Blood Cell (WBC) segmentation is one of the important topics in the medical image processin... more White Blood Cell (WBC) segmentation is one of the important topics in the medical image processing field. Many researchers proposed several clustering approaches to segment WBC from blood smear microscopic images. However, a fast and robust segmentation of WBCs is still a challenging task. In this work, we propose parallel algorithms that utilize the parallelism capabilities of the Graphics Processing Units (GPUs) to accelerate the segmentation of WBC from microscopic images. In this research, we implement the main image segmentation clustering algorithms using one thread that we run on a single CPU (sequential implementation) and using multiple threads that we run on both the CPU and the GPU (hybrid CPU-GPU). We focus our work on the most common four segmentation algorithms: Standard K-means (SKM), Adaptive K-means (AKM), Fuzzy C-means (FCM), and Fuzzy Possibilistic C-means (FPCM). We implement these algorithms and the pre-processing steps for WBC image segmentation in CUDA programming to take the advantages of the large number of cores in GPUs. In this work, our hybrid implementation accelerated the four studied sequential algorithms by 4X, 3.8X, 3.4X, and 3.4X, respectively, without affecting WBC segmentation quality.

International Journal of Electrical and Computer Engineering (IJECE), 2021

Question-answering platforms serve millions of users seeking knowledge and solutions for their da... more Question-answering platforms serve millions of users seeking knowledge and solutions for their daily life problems. However, many knowledge seekers are facing the challenge to find the right answer among similar answered questions and writer’s responding to asked questions feel like they need to repeat answers many times for similar questions. This research aims at tackling the problem of learning the semantic text similarity among different asked questions by using deep learning. Three models are implemented to address the aforementioned problem: i) a supervised-machine learning model using XGBoost trained with pre-defined features, ii) an adapted Siamese-based deep learning recurrent architecture trained with pre-defined features, and iii) a Pre-trained deep bidirectional transformer based on BERT model. Proposed models were evaluated using a reference Arabic dataset from the mawdoo3.com company. Evaluation results show that the BERT-based model outperforms the other two models wi...

International Journal of Electrical and Computer Engineering (IJECE), 2021

Diabetic retinopathy is an eye disease caused by high blood sugar and pressure which damages the ... more Diabetic retinopathy is an eye disease caused by high blood sugar and pressure which damages the blood vessels in the eye. Diabetic retinopathy is the root cause of more than 1% of the blindness worldwide. Early detection of this disease is crucial as it prevents it from progressing to a more severe level. However, the current machine learning-based approaches for detecting the severity level of diabetic retinopathy are either, i) rely on manually extracting features which makes an approach unpractical, or ii) trained on small dataset thus cannot be generalized. In this study, we propose a transfer learning-based approach for detecting the severity level of the diabetic retinopathy with high accuracy. Our model is a deep learning model based on global average pooling (GAP) technique with various pre-trained convolutional neural net- work (CNN) models. The experimental results of our approach, in which our best model achieved 82.4% quadratic weighted kappa (QWK), corroborate the abil...

2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS), 2018

With the advent of Next-Generation Sequencing (NGS) technologies, the needs for computing power, ... more With the advent of Next-Generation Sequencing (NGS) technologies, the needs for computing power, storage, and several bioinformatics tools are getting urgent. Cloud computing is a promising solution for such computationally intensive problems. In this work, we provide a review of the most NGS tools that are running on the cloud to analysis the big multi-omics data involved in NGS platforms. This study provides a comprehensive overview of the most important NGS tools that are used and operated on cloud platforms. We reported features and the requirements of each tools in details. To the best of our knowledge, a comprehensive recent review covering all cloud-based NGS platforms has not been reported yet. In this review, we comprehensively study 20 could-based tools used for NGS data analysis. We extensively analyze and classify these NGS tools in order to provide guiding overview for NGS researchers.

2018 6th International Conference on Multimedia Computing and Systems (ICMCS), 2018

Recently, 3D model reconstruction becomes a reality. That is because of using many algorithms tha... more Recently, 3D model reconstruction becomes a reality. That is because of using many algorithms that are implemented as automated tools and the ability to process dozens of images which might be calibrated or uncalibrated. When dealing with uncalibrated images, more processing time is usually required to perform "self-calibration". When using uncalibrated images, the images are usually not in perfect quality due to the uncalibrated nature of the capturing process. For this reason, this paper aims to study the impact of using image enhancement techniques on the quality of the building process of 3D models. This work mainly focus on the contrast of images. After applying the preprocessing procedures, the image sets where used to build the 3D models using three software kits (COLMAP, VSFM and Agisoft Photoscan). The results show that applying histogram equalization enhances the quality of the generated 3D models.