White Blood Cell Classification Using Texture and RGB Features of Oversampled Microscopic Images

Article Subjects > Biomedicine
Subjects > Engineering
Europe University of Atlantic > Research > Scientific Production
Ibero-american International University > Research > Scientific Magazines
Ibero-american International University > Research > Scientific Production
Universidad Internacional do Cuanza > Research > Scientific Production
Abierto Inglés White blood cell (WBC) type classification is a task of significant importance for diagnosis using microscopic images of WBC, which develop immunity to fight against infections and foreign substances. WBCs consist of different types, and abnormalities in a type of WBC may potentially represent a disease such as leukemia. Existing studies are limited by low accuracy and overrated performance, often caused by model overfit due to an imbalanced dataset. Additionally, many studies consider a lower number of WBC types, and the accuracy is exaggerated. This study presents a hybrid feature set of selective features and synthetic minority oversampling technique-based resampling to mitigate the influence of the above-mentioned problems. Furthermore, machine learning models are adopted for being less computationally complex, requiring less data for training, and providing robust results. Experiments are performed using both machine- and deep learning models for performance comparison using the original dataset, augmented dataset, and oversampled dataset to analyze the performances of the models. The results suggest that a hybrid feature set of both texture and RGB features from microscopic images, selected using Chi2, produces a high accuracy of 0.97 with random forest. Performance appraisal using k-fold cross-validation and comparison with existing state-of-the-art studies shows that the proposed approach outperforms existing studies regarding the obtained accuracy and computational complexity. metadata Rustam, Furqan and Aslam, Naila and De La Torre Díez, Isabel and Khan, Yaser Daanial and Vidal Mazón, Juan Luis and Rodríguez Velasco, Carmen Lilí and Ashraf, Imran mail UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, juanluis.vidal@uneatlantico.es, carmen.rodriguez@uneatlantico.es, UNSPECIFIED (2022) White Blood Cell Classification Using Texture and RGB Features of Oversampled Microscopic Images. Healthcare, 10 (11). p. 2230. ISSN 2227-9032

[img] Text
healthcare-10-02230 (1).pdf
Available under License Creative Commons Attribution.

Download (20MB)

Abstract

White blood cell (WBC) type classification is a task of significant importance for diagnosis using microscopic images of WBC, which develop immunity to fight against infections and foreign substances. WBCs consist of different types, and abnormalities in a type of WBC may potentially represent a disease such as leukemia. Existing studies are limited by low accuracy and overrated performance, often caused by model overfit due to an imbalanced dataset. Additionally, many studies consider a lower number of WBC types, and the accuracy is exaggerated. This study presents a hybrid feature set of selective features and synthetic minority oversampling technique-based resampling to mitigate the influence of the above-mentioned problems. Furthermore, machine learning models are adopted for being less computationally complex, requiring less data for training, and providing robust results. Experiments are performed using both machine- and deep learning models for performance comparison using the original dataset, augmented dataset, and oversampled dataset to analyze the performances of the models. The results suggest that a hybrid feature set of both texture and RGB features from microscopic images, selected using Chi2, produces a high accuracy of 0.97 with random forest. Performance appraisal using k-fold cross-validation and comparison with existing state-of-the-art studies shows that the proposed approach outperforms existing studies regarding the obtained accuracy and computational complexity.

Item Type: Article
Uncontrolled Keywords: white blood cells classification; leukemia; texture features; Chi-squared; SMOTE
Subjects: Subjects > Biomedicine
Subjects > Engineering
Divisions: Europe University of Atlantic > Research > Scientific Production
Ibero-american International University > Research > Scientific Magazines
Ibero-american International University > Research > Scientific Production
Universidad Internacional do Cuanza > Research > Scientific Production
Date Deposited: 16 Nov 2022 23:30
Last Modified: 16 Nov 2022 23:30
URI: https://repositorio.unic.co.ao/id/eprint/4607

Actions (login required)

View Item View Item

<a href="/489/1/ijerph-19-00849.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Detection of Upper Limb Asymmetries in Athletes According to the Stage of the Season—A Longitudinal Study

Abstract: Sports injuries can affect the performance of athletes. For this reason, functional tests are used for injury assessment and prevention, analyzing physical or physiological imbalances and detecting asymmetries. The main aim of this study was to detect the asymmetries in the upper limbs (right and left arms) in athletes, using the OctoBalance Test (OB), depending on the stage of the season. Two hundred and fifty-two participants (age: 23.33 ± 8.96 years old; height: 178.63 ± 11.12 cm; body mass: 80.28 ± 17.61 kg; body mass index: 24.88 ± 4.58; sports experience: 12.52 ± 6.28 years), practicing different sports (rugby, athletics, football, swimming, handball, triathlon, basketball, hockey, badminton and volleyball), assessed with the OB in medial, superolateral, and inferolateral directions in both arms, in four moments of the season (May 2017, September 2017, February 2018 and May 2018). ANOVA test was used with repeated measures with a p ≤ 0.05, for the analysis of the different studied variances. Significant differences were found (p = 0.021) in the medial direction of the left arm, between the first (May 2017) and fourth stages (May 2018), with values of 71.02 ± 7.15 cm and 65.03 ± 7.66 cm. From the detection of asymmetries, using the OB to measure, in the medial, superolateral and inferolateral directions, mobility and balance can be assessed. In addition, it is possible to observe functional imbalances, as a risk factor for injury, in each of the stages into which the season is divided, which will help in the prevention of injuries and in the individualization of training.

Producción Científica

Álvaro Velarde-Sotres mail alvaro.velarde@uneatlantico.es, Antonio Bores-Cerezal mail antonio.bores@uneatlantico.es, Marcos Mecías-Calvo mail marcos.mecias@uneatlantico.es, Martín Barcala Furelos mail martin.barcala@uneatlantico.es, Silvia Aparicio Obregón mail silvia.aparicio@uneatlantico.es, Julio Calleja-González mail ,

Velarde-Sotres

<a class="ep_document_link" href="/490/1/sustainability-14-00913-v2.pdf"><img class="ep_doc_icon" alt="[img]" src="/490/1.hassmallThumbnailVersion/sustainability-14-00913-v2.pdf" border="0"/></a>

en

open

Blockchain Interoperability: Towards a Sustainable Payment System

The highly fragmented blockchain and cryptocurrency ecosystem necessitates interoperability mechanisms as a requirement for blockchain-technology acceptance. The immediate implication of interchain interoperability is automatic swapping between cryptocurrencies. We performed a systematic review of the existing literature on Blockchain interoperability and atomic cross-chain transactions. We investigated different blockchain interoperability approaches, including industrial solutions, categorized them and identified the key mechanisms used, and list several example projects for each category. We focused on the atomic transactions between blockchain, a process also known as atomic swap. Furthermore, we studied recent implementations along with architectural approaches for atomic swap and deduced research issues and challenges in cross-chain interoperability and atomic swap. Atomic swap can instantly transfer tokens and significantly reduce the associated costs without using any centralized authority, and thus facilitates the development of a sustainable payment system for wider financial inclusion.

Producción Científica

Debasis Mohanty mail , Divya Anand mail , Hani Moaiteq Aljahdali mail , Santos Gracia Villar mail santos.gracia@uneatlantico.es,

Mohanty

en

close

Role of Network Slicing in Software Defined Networking for 5G: Use Cases and Future Directions

Network slicing is expected to be critical in the deployment of 5G mobile networks and systems. On top of a single physical infrastructure, the technology enables operators to operate several virtual networks. As the 5G commercialization was recently deployed, network function virtualization (NFV) and software-defined networking (SDN) will drive network slicing. In this article, we present an overview of SDN in 5G, and the motivation, role, and market growth of network slicing. We then discuss usage scenarios of SDN in network slicing for 5G. The proposed architecture comprises the three usage scenarios: enhanced mobile broadband (eMBB) provides the support to varying types of services used; ultra-reliable low-latency communications (URLLC) provides a certain class of applications such as higher bandwidth, high definition video streaming, mobile TV, and so on; massive machine type communications (mMTC) throws light on the types of services used to connect huge numbers of devices. Finally, challenges and solutions based on network slicing in 5G are presented.

Producción Científica

Himanshi Babbar mail , Shalli Rani mail , Ahmad Ali AlZubi mail , Aman Singh mail aman.singh@uneatlantico.es, Nidal Nasser mail , Asmaa Ali mail ,

Babbar

<a class="ep_document_link" href="/670/1/TSP_CMC_47454.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Intelligent Approach for Clustering Mutations’ Nature of COVID-19 Genome

In December 2019, a group of people in Wuhan city of Hubei province of China were found to be affected by an infection called dark etiology pneumonia. The outbreak of this pneumonia infection was declared a deadly disease by the China Center for Disease Control and Prevention on January 9, 2020, named Novel Coronavirus 2019 (nCoV-2019). This nCoV-2019 is now known as COVID-19. There is a big list of infections of this coronavirus which is present in the form of a big family. This virus can cause several diseases that usually develop with a serious problem. According to the World Health Organization (WHO), 2019-nCoV has been placed as the modern generation of Severe Acute Respiratory Syndrome (SARS) and Middle East Respiratory Syndrome (MERS) coronaviruses, so COVID-19 can repeatedly change its internal genome structure to extend its existence. Understanding and accurately predicting the mutational properties of the genome structure of COVID-19 can form a good leadership role in preventing and fighting against coronavirus. In this research paper, an analytical approach has been presented which is based on the k-means cluster technique of machine learning to find the clusters over the mutational properties of the COVID-19 viruses’ complete genome. This method would be able to act as a promising tool to monitor and track pathogenic infections in their stable and local genetics/hereditary varieties. This paper identifies five main clusters of mutations with as best in most cases in the coronavirus that could help scientists and researchers develop disease control vaccines for the transformation of coronaviruses.

Producción Científica

Ankur Dumka mail , Parag Verma mail , Rajesh Singh mail , Anuj Bhardwaj mail , Khalid Alsubhi mail , Divya Anand mail divya.anand@uneatlantico.es, Irene Delgado Noya mail irene.delgado@uneatlantico.es, Silvia Aparicio Obregón mail silvia.aparicio@uneatlantico.es,

Dumka

<a class="ep_document_link" href="/672/1/TSP_CMC_47459.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

A Novel Deep Learning Based Healthcare Model for COVID-19 Pandemic Stress Analysis

Coronavirus (COVID-19) has impacted nearly every person across the globe either in terms of losses of life or as of lockdown. The current coronavirus (COVID-19) pandemic is a rare/special situation where people can express their feelings on Internet-based social networks. Social media is emerging as the biggest platform in recent years where people spend most of their time expressing themselves and their emotions. This research is based on gathering data from Twitter and analyzing the behavior of the people during the COVID-19 lockdown. The research is based on the logic expressed by people in this perspective and emotions for the suffering of COVID-19 and lockdown. In this research, we have used a Long Short-Term Memory (LSTM) network model with Convolutional Neural Network using Keras python deep-learning library to determine whether social media platform users are depressed in terms of positive, negative, or neutral emotional out bust based on their Twitter posts. The results showed that the model has 88.14% accuracy (representation of the correct prediction over the test dataset) after 10 epochs which most tweets showed had neutral polarity. The evaluation shows interesting results in positive (1), negative (–1), and neutral (0) emotions through different visualization.

Producción Científica

Ankur Dumka mail , Parag Verma mail , Rajesh Singh mail , Anil Kumar Bisht mail , Divya Anand mail divya.anand@uneatlantico.es, Hani Moaiteq Aljahdali mail , Irene Delgado Noya mail irene.delgado@uneatlantico.es, Silvia Aparicio Obregón mail silvia.aparicio@uneatlantico.es,

Dumka