Preferred Language
Articles
/
6ebpzp0BmraWrQ4dE1vp
Predicting Bitter Orange (Citrus aurantium L.) Maturity by Machine Learning Based on Picking Force in Smart Picker
...Show More Authors

Manual fruit picking is labor-intensive and can damage fruit. Fully mechanized picking is efficient, but it also risks fruit damage. Therefore, semi-automated tools are needed to improve bitter orange picking. This paper presents a smart manual picker designed to facilitate picking while predicting fruit maturity based on picking force as well as various chemical and physical parameters using machine learning (ML). The study methodology consists of five stages: (1) manufacturing the smart picker, (2) picking 50 bitter orange samples, (3) measuring the characteristics of the bitter oranges in the laboratory, (4) training different ML models, and (5) identifying the most accurate model for predicting fruit maturity. The results indicate that as fruits mature, their weight, CIE-L*a*b* values, and pH levels increase, while picking force and hardness decrease. Notably, picking force exhibited a strong correlation (93.5%) with maturity compared to other physical parameters. The Kruskal–Wallis test also showed that the relationship between picking force and bitter orange physical parameters, including weight, CIE-L*a*b*, pH, and hardness, was statistically significant. The extreme gradient boosting (XGBoost) model achieved the highest training accuracy (100%), outperforming stacking (99.91%), random forest (91.17%), and gradient boosting machine (89.08%) on all evaluation metrics. However, the stacking model is considered better, even though XGBoost achieved 100% training accuracy, as the former showed a better balance between training, testing, and validation. This study contributes to improving bitter orange quality by accurately predicting maturity through data collected from the smart picker.

Scopus Crossref
View Publication
Publication Date
Thu Jan 01 2015
Journal Name
International Journal Of Applied Agricultural Sciences
Effect of Salt Stress on Some Growth Indicators and Cellular Components of Wheat (<i>Triticum aestivum</i> L.) Callus
...Show More Authors

The experiment was conducted to study the effect of sodium chloride (NaCl) at the concentrations of 0.0, 0.5, 1.0 and 1.5% on the callus cells. The Iraq wheat variety was grown in vitro for the purpose of knowing the effect of salt stress on some indicators and cellular components of callus by using a randomized complete design, at the laboratories of tissue culture propagation date palm unit in the College of Agriculture / University of Kufa during the period 2014-2015. Fresh and dry weight, the rate of absolute growth, percentage of dry matter of callus, content of the callus cells of proline, total soluble carbohydrates, sodium and potassium ions, effectiveness of the enzymes catalase and peroxidase study shock salt proteins in callus we

... Show More
View Publication
Crossref (1)
Crossref
Publication Date
Wed Sep 01 2021
Journal Name
Baghdad Science Journal
Effects of Nitrogen and Sulfur Sprays on the Growth and Production of Broccoli Brassica Oleracea var. Italica L.: nitrogen and sulfur spray enhance broccoli growth and production
...Show More Authors

In order to achieve optimal plant growth and production, essential nutrients must be readily available in adequate quantities and in a balanced proportion to give a good yield, especially broccoli which has health benefits that may not be found in many other plants. For this purpose, this experiment was carried out during the seasons 2019/2020 in the botanical garden of the Department of Biology, College of Science for Women, University of Baghdad, to study the effects of nitrogen and sulphur and their interaction on eight parameters reflecting the overall traits of vegetative growth, yield, and chlorophyll content of broccoli Brassica oleracea L. (var. italic JASSMINE F1 Hybrid). A factorial design with three replicates was use

... Show More
View Publication Preview PDF
Scopus (14)
Crossref (5)
Scopus Clarivate Crossref
Publication Date
Thu Jun 20 2024
Journal Name
Bulletin Of The Iraq Natural History Museum
MOLECULAR STUDY OF SOME SPECIES OF CENTIPEDES IN IRAQ WITH NEW RECORD OF LITHOBIUS CRASSIPES L. KOCH, 1862 (CHILOPODA, LITHOBIOMORPHA, LITHOBIIDAE)
...Show More Authors

The first molecular research on Iraqi centipede fauna is presented in this article. Between October 2022 and May 2023, during various climatic circumstances, centipedes were collected from several locations in four provinces of Iraq. Three families, represented by four genera, underwent molecular identification, and five species were found. From the order Scolopendromorpha family Scolopendridae, two species were recorded, Scolopendra morsitans Linnaeus, 1758, and S. cingulata Latreille, 1829, Cormocephalus sp.; while from the order Lithobiomorpha, family Lithobiidae, one species was recorded for first time in Iraq; Lithobius crassipes L. Koch, 1862 from the order Geophilomorpha family Himantariidae, one species Bothriogaster Signata

... Show More
View Publication
Scopus (1)
Crossref (1)
Scopus Crossref
Publication Date
Tue Feb 14 2017
Journal Name
Human And Ecological Risk Assessment: An International Journal
Biochemical and hematological parameters and histological alterations in fish <i>Cyprinus carpio</i> L. as biomarkers for water pollution with chlorpyrifos
...Show More Authors

View Publication
Scopus (22)
Crossref (21)
Scopus Clarivate Crossref
Publication Date
Tue Sep 27 2022
Journal Name
Al–bahith Al–a'alami
Motives for public exposure to advertisement through smart phone applications and its purchasing decisions relationship (A research drawn from a Master Degree thesis)
...Show More Authors

Advertisement on smart phone shopping apps are a new way of driving users to satisfy their needs and influence their purchasing decisions, In this way, the research could be aimed to know The role of the relationship between the motivations for audience exposure to shopping apps advertisement and purchasing decisions, In order to achieve the objectives of the research, the researcher adopted the survey method and used the questionnaire and the scale to collect data and information, The researcher chose the "random sample multi stages", The sample size was (475) respondents from Baghdad city center (18 years and above) women and men.

View Publication Preview PDF
Crossref
Publication Date
Fri Jun 26 2026
Journal Name
Al.qadisiya Journal For The Sciences Of Physical Education
The Influence of Using Special Exercises with Weights to Develop Moments of Force to Some of the Striking Shoulder and Arm Muscles and Accuracy of the Skill of the Smash and Rectum in Volleyball
...Show More Authors

This research is an attempt to develop exercise with weights to strengthen some of the striking muscles in the shoulder and arm and to develop the accuracy of the smash and rectum skills. The importance of this paper lies in the study of moments of force to achieve the ability to control muscular work and to explore the impact of physical and skill exercises with weights to develop moments of force for some muscles. The experimental method on a sample of players, selected according to the intentional method, including ( 9) advanced players representing Air Force Club participating in the Premier League for season 2011-2012. It is concluded that the exercises proposed have their effective impact on developing the variables of moments force f

... Show More
View Publication
Publication Date
Tue Mar 01 2016
Journal Name
International Journal Of Engineering Research And Advanced Technology (ijerat)
Speeding Up Back-Propagation Learning (SUBPL) Algorithm: A New Modified Back_Propagation Algorithm
...Show More Authors

The convergence speed is the most important feature of Back-Propagation (BP) algorithm. A lot of improvements were proposed to this algorithm since its presentation, in order to speed up the convergence phase. In this paper, a new modified BP algorithm called Speeding up Back-Propagation Learning (SUBPL) algorithm is proposed and compared to the standard BP. Different data sets were implemented and experimented to verify the improvement in SUBPL.

View Publication
Publication Date
Tue Jul 01 2025
Journal Name
Mastering The Minds Of Machines
Unsupervised Learning: Discovering Patterns without Labels: Health Care, E-Commerce, and Cybersecurity
...Show More Authors

View Publication
Scopus Crossref
Publication Date
Mon Jun 01 2026
Journal Name
Iraqi Journal For Computers And Informatics
Explainable Federated Learning for Brain Tumor Classification Using Multi-Source MRI Data
...Show More Authors

Early diagnosis and clinical decision-making depend on accurate brain tumor classification using magnetic resonance imaging (MRI). However, traditional deep learning methods usually rely on centralized medical data, which raises privacy concerns and limits the use of distributed clinical data. This research proposes a privacy-preserving federated learning framework for MRI image-based binary brain tumor classification using a decentralized ResNet-18 architecture that enables collaborative training without sharing raw patient data. To reflect realistic clinical conditions, the framework integrates heterogeneous multi-source datasets in different image formats (PNG and JPG) and evaluates performance under both IID and non-IID settings

... Show More
View Publication Preview PDF
Crossref
Publication Date
Mon Mar 31 2025
Journal Name
International Journal Of Advanced Technology And Engineering Exploration
Breast cancer survival rate prediction using multimodal deep learning with multigenetic features
...Show More Authors

Breast cancer is a heterogeneous disease characterized by molecular complexity. This research utilized three genetic expression profiles—gene expression, deoxyribonucleic acid (DNA) methylation, and micro ribonucleic acid (miRNA) expression—to deepen the understanding of breast cancer biology and contribute to the development of a reliable survival rate prediction model. During the preprocessing phase, principal component analysis (PCA) was applied to reduce the dimensionality of each dataset before computing consensus features across the three omics datasets. By integrating these datasets with the consensus features, the model's ability to uncover deep connections within the data was significantly improved. The proposed multimodal deep

... Show More
View Publication Preview PDF
Scopus Crossref