6 research outputs found
Investigating the use of ensemble techniques in predicting object-oriented software maintainability
No full textContext: Prediction of the maintainability of classes in object-oriented systems is a significant factor for software success; however, it is a challenging task. Although prior object-oriented software maintainability literature acknowledges the role of machine learning techniques as valuable predictors of potential change, the most suitable technique that consistently achieves high accuracy remains undetermined and there is no clear indication of which techniques are more appropriate.;Objective: This thesis aims to empirically investigate the capability of ensemble models to provide an increased prediction accuracy, compared with individual models, by applying them on several software maintainability datasets using different base models and analysing the impact of parameter tuning.;Method: In the first part of this thesis, a systematic review of studies related to the prediction of the maintainability of object-oriented software systems using machine learning techniques is presented. In the remaining parts of this thesis, three empirical studies were performed to evaluate and compare different homogeneous and heterogeneous ensemble models against sets of individual models for predicting software maintainability of object-oriented systems at the class level. These models were employed on 14 datasets that were extracted from the maintenance of object-oriented software systems.;Results: The systematic literature review determined 56 relevant studies and indicated that the application of ensemble models is relatively rare, thus there is a need to perform studies using these models as well as others to an extensive variety of datasets. The results obtained from three empirical studies indicate that the proposed ensemble models yield improved prediction accuracy over most of the individual models. This improvement was significant only in the third empirical study, along with a few cases in the second empirical study. In most cases, nearest neighbours or support vector regression achieved the best prediction accuracy among individual models; moreover, these models as a base model in bagging and additive regression outperformed other prediction models, along with random forest.;Conclusion: The main finding is that ensemble models are effective for predicting software maintainability and they are more accurate than some individual models; their performance may be improved by using large datasets, or parameter tuning. Also, ensemble models improve the performance of weaker base models.Context: Prediction of the maintainability of classes in object-oriented systems is a significant factor for software success; however, it is a challenging task. Although prior object-oriented software maintainability literature acknowledges the role of machine learning techniques as valuable predictors of potential change, the most suitable technique that consistently achieves high accuracy remains undetermined and there is no clear indication of which techniques are more appropriate.;Objective: This thesis aims to empirically investigate the capability of ensemble models to provide an increased prediction accuracy, compared with individual models, by applying them on several software maintainability datasets using different base models and analysing the impact of parameter tuning.;Method: In the first part of this thesis, a systematic review of studies related to the prediction of the maintainability of object-oriented software systems using machine learning techniques is presented. In the remaining parts of this thesis, three empirical studies were performed to evaluate and compare different homogeneous and heterogeneous ensemble models against sets of individual models for predicting software maintainability of object-oriented systems at the class level. These models were employed on 14 datasets that were extracted from the maintenance of object-oriented software systems.;Results: The systematic literature review determined 56 relevant studies and indicated that the application of ensemble models is relatively rare, thus there is a need to perform studies using these models as well as others to an extensive variety of datasets. The results obtained from three empirical studies indicate that the proposed ensemble models yield improved prediction accuracy over most of the individual models. This improvement was significant only in the third empirical study, along with a few cases in the second empirical study. In most cases, nearest neighbours or support vector regression achieved the best prediction accuracy among individual models; moreover, these models as a base model in bagging and additive regression outperformed other prediction models, along with random forest.;Conclusion: The main finding is that ensemble models are effective for predicting software maintainability and they are more accurate than some individual models; their performance may be improved by using large datasets, or parameter tuning. Also, ensemble models improve the performance of weaker base models
Leveraging Metaheuristic Unequal Clustering for Hotspot Elimination in Energy-Aware Wireless Sensor Networks
No full textWireless sensor networks (WSNs) are becoming a significant technology for ubiquitous living and continue to be involved in active research because of their varied applications. Energy awareness will be a critical design problem in WSNs. Clustering is a widespread energy-efficient method and grants several benefits such as scalability, energy efficiency, less delay, and lifetime, but it results in hotspot issues. To solve this, unequal clustering (UC) has been presented. In UC, the size of the cluster differs with the distance to the base station (BS). This paper devises an improved tuna-swarm-algorithm-based unequal clustering for hotspot elimination (ITSA-UCHSE) technique in an energy-aware WSN. The ITSA-UCHSE technique intends to resolve the hotspot problem and uneven energy dissipation in the WSN. In this study, the ITSA is derived from the use of a tent chaotic map with the traditional TSA. In addition, the ITSA-UCHSE technique computes a fitness value based on energy and distance metrics. Moreover, the cluster size determination via the ITSA-UCHSE technique helps to address the hotspot issue. To demonstrate the enhanced performance of the ITSA-UCHSE approach, a series of simulation analyses were conducted. The simulation values stated that the ITSA-UCHSE algorithm has reached improved results over other models
Intelligent Deep-Learning-Enabled Decision-Making Medical System for Pancreatic Tumor Classification on CT Images
No full textDecision-making medical systems (DMS) refer to the design of decision techniques in the healthcare sector. They involve a procedure of employing ideas and decisions related to certain processes such as data acquisition, processing, judgment, and conclusion. Pancreatic cancer is a lethal type of cancer, and its prediction is ineffective with current techniques. Automated detection and classification of pancreatic tumors can be provided by the computer-aided diagnosis (CAD) model using radiological images such as computed tomography (CT) and magnetic resonance imaging (MRI). The recently developed machine learning (ML) and deep learning (DL) models can be utilized for the automated and timely detection of pancreatic cancer. In light of this, this article introduces an intelligent deep-learning-enabled decision-making medical system for pancreatic tumor classification (IDLDMS-PTC) using CT images. The major intention of the IDLDMS-PTC technique is to examine the CT images for the existence of pancreatic tumors. The IDLDMS-PTC model derives an emperor penguin optimizer (EPO) with multilevel thresholding (EPO-MLT) technique for pancreatic tumor segmentation. Additionally, the MobileNet model is applied as a feature extractor with optimal auto encoder (AE) for pancreatic tumor classification. In order to optimally adjust the weight and bias values of the AE technique, the multileader optimization (MLO) technique is utilized. The design of the EPO algorithm for optimal threshold selection and the MLO algorithm for parameter tuning shows the novelty. A wide range of simulations was executed on benchmark datasets, and the outcomes reported the promising performance of the IDLDMS-PTC model on the existing methods
Design of a peptide-based vaccine against human respiratory syncytial virus using a reverse vaccinology approach: evaluation of immunogenicity, antigenicity, allergenicity, and toxicity.
No full textBackground: Attempts to develop an hRSV vaccine have faced safety and efficacy challenges, with only three FDA-approved vaccines (Moderna’s Mresvia, Pfizer’s Abrysvo, and GSK’s Arexvy) available. These vaccines are limited to individuals over 60 years, require boosters, and only reduce disease severity without clearing the infection. Therefore, we employed a reverse vaccinology approach in this study to identify the most promising antigenic epitopes capable of eliciting a robust and protective immune response.
Methodology: This study employed computational techniques to design a novel multi-epitope vaccine targeting hRSV. Using bioinformatics tools, candidate epitopes were identified from conserved viral proteins (F and G glycoproteins), assessing their immunogenicity, antigenicity, and allergenicity. Key tools included ExPASy, ProtParam, VaxiJen v2.0, AllergenFP v1.0, AllerTOP v2.0, NetCTL v1.2, IEDB, and Toxin-Pred. The vaccine construct was assessed for stability and toxicity through in silico analyses. We then characterized its kinetic properties, evaluated its structural integrity, and analyzed its interactions with Toll-like receptors (TLRs) using molecular docking, modeling, and refinement with AlphaFold3 and ClusPro.
Results: The designed constructs showed strong antigenicity (0.5996 for F-based and 0.6048 for G-based vaccine), non-allergenicity, and stability (instability index <40). Among these, most amino acids were in the extracellular domain of the construct. Molecular docking and dynamics simulations indicated strong binding interactions with TLR1 and TLR4 and minimal RMSF fluctuations, which ensured structural stability. Strong humoral and cellular responses were suggested by in silico immune simulation demonstrating robust immune activation, with high levels of IgG, IgM, IL-2, and IFN-γ. The physical and chemical analyses revealed that the majority of amino acids from the F and G proteins were located in the extracellular domain of the construct. The presence of signal peptide cleavage sites in both glycoprotein components further facilitates antigen presentation to the immune system.
Conclusions: This study presents a promising peptide-based vaccine candidate against hRSV that can effectively engage the immune system, showing strong immunogenicity and antigenicity. Future in vitro and in vivo studies are essential to evaluate the ability of the multi-epitope vaccine candidate to stimulate both humoral and cell-mediated immune responses and to assess its efficacy and safety profile.The author(s) declare that financial support was received for the research and/or publication of this article. The authors extend their appreciation to the Researchers Supporting Project number (RSP2025R506), King Saud University, Riyadh, Saudi Arabia for supporting this work.The authors would like to thank the Research Center at King Fahad Medical City for their valuable technical suppor
Paper Mapping Asia plants: Current status on floristic information in Southwest Asia
No full textMapping Asia Plants (MAP) is a comprehensive project that aims to build a detailed infrastructure for integrating Asian plant distribution data a global-scale array of knowledge for plant biodiversity conservation. Here, we provide a brief historical review of botanical research in Southwest Asia an understudied botanical region with high conservation priority. Nineteen countries were included in this study (from west to east): Turkey, Cyprus, Palestine, Israel, Jordan, Saudi Arabia, Lebanon, Syria, Iraq, Georgia, Yemen, Armenia, Iran, Azerbaijan, Kuwait, Bahrain, Qatar, United Arab Emirates, and Oman. We reviewed 132 resources comprising 125 Floras and Checklists, of which we describe in some detail at least one of the most important Floras or Checklists for each country. Complete and published national Floras exist for 13 countries; three countries (Jordan, Israel and Bahrain) do not have a Flora but have annotated Checklists, and national Floras are at different stages of completion for Iran, Iraq and Georgia. Where present, online resources are also given for references. We found major gaps in species concepts and taxonomic classification systems, and that many up-to-date Flora revisions remained unresolved, i.e. taxon ranks and species concepts varied among different countries, different systems were adopted or followed in the taxonomic treatments in the Floras and Checklists, and some of the current Floras are out of date. Floras are the first necessary step for many fields, including evolutionary biology, ecology, biogeography, and systematics, as well as environmental research and conservation of biodiversity at national and international levels. Here, we provide the progress updates on the main published floristic works of Southwest Asia, which continue to serve as references for the Flora of Southwest Asia, and will be the foundation of the MAP project. (C) 2020 The Author(s). Published by Elsevier B.V
SARS-CoV-2 susceptibility and COVID-19 disease severity are associated with genetic variants affecting gene expression in a variety of tissues
No full textVariability in SARS-CoV-2 susceptibility and COVID-19 disease severity between individuals is partly due to genetic factors. Here, we identify 4 genomic loci with suggestive associations for SARS-CoV-2 susceptibility and 19 for COVID-19 disease severity. Four of these 23 loci likely have an ethnicity-specific component. Genome-wide association study (GWAS) signals in 11 loci colocalize with expression quantitative trait loci (eQTLs) associated with the expression of 20 genes in 62 tissues/cell types (range: 1:43 tissues/gene), including lung, brain, heart, muscle, and skin as well as the digestive system and immune system. We perform genetic fine mapping to compute 99% credible SNP sets, which identify 10 GWAS loci that have eight or fewer SNPs in the credible set, including three loci with one single likely causal SNP. Our study suggests that the diverse symptoms and disease severity of COVID-19 observed between individuals is associated with variants across the genome, affecting gene expression levels in a wide variety of tissue types. © 2021 The Author(s
