Ontology-based Soft Computing and Machine Learning Model for Efficient Retrieval DOI Creative Commons
Sanjay Kumar Anand, Suresh Kumar

Research Square (Research Square), Journal Year: 2022, Volume and Issue: unknown

Published: Dec. 5, 2022

Abstract Unstructured and unorganized data always degrade the performance of search techniques produce irrelevant results in response to query as well decrease speed retrieval results. Ontology Semantic Web (SW) provides an adequate solution represent knowledge, because its backbone knowledge application or domain. But, a domain ontology has three basic problems while retrieving useful from ontology- structuring/arrangement, unnecessary reduction, selection extraction, speeding up process. To handle such problem, MLK-rBO model is proposed that works for four different phases- clustering, discovery, building probabilistic network, evaluation using ensemble approach namely rough set, Bayesian network (BN). Finally, tested with statistical parameters compared other models DT, RF, SVM check effectiveness MLK-rBO. By analyzing experimental results, we observed gives better accuracy (98.36 \%) than available models.

Language: Английский

A comparative study of machine learning models with LASSO and SHAP feature selection for breast cancer prediction DOI Creative Commons
Md. Shazzad Hossain Shaon, Tasmin Karim, Shahriar Shakil

et al.

Healthcare Analytics, Journal Year: 2024, Volume and Issue: 6, P. 100353 - 100353

Published: June 25, 2024

In recent decades, breast cancer has become the most prevalent type of that impacts women in world, which shows a significant risk to death rates women. Early identification might drastically decrease patient mortality and greatly improve chance an effective treatment. modern times, machine learning models have crucial for classifying strengthening both accuracy efficiency diagnostic medical treatment strategies. Therefore, this study is focused on early detection using variety algorithms desires identify feature selection process with amalgamated dataset. Initially, we evaluated five traditional two meta-models separate datasets. To find valuable features, used Least Absolute Shrinkage Selection Operator (LASSO) as well SHapley Additive exPlanations (SHAP) methods analyzed them through wide range performance regulations. Additionally, applied these combined dataset observed mergeddataset was significantly beneficial diagnosis. After analyzing strategies, it demonstrated majority performed more accurately when utilizing SHAP methodologies. Notably, three meta-classifiers obtained 99.82%, demonstrating superior compared state-of-the-art methods. This advancement holds role lays foundation refining tools enhancing progression science field.

Language: Английский

Citations

11

Effectiveness of applying Machine Learning techniques and Ontologies in Breast Cancer detection DOI Open Access
Hakim El Massari, Noreddine Gherabi, Sajida Mhammedi

et al.

Procedia Computer Science, Journal Year: 2023, Volume and Issue: 218, P. 2392 - 2400

Published: Jan. 1, 2023

Breast cancer is a disease that primarily affects women, but it can also affect men, although in much smaller percentage. Recently, doctors have made great strides this trend of early detection and treatment breast to reduce the number deaths caused by serious disease. Moreover, researchers are analyzing massive amounts sophisticated medical data using combination statistical machine learning approaches help clinicians predict cancer. In presented work, an ontological model based on decision tree algorithm capable reliably predicting has been demonstrated. The method consists extracting rules from distinguish between malignant benign patients, then implementing these reasoner via Semantic Web Rule Language (SWRL). results indicated achieved highest prediction accuracy 97.10%.

Language: Английский

Citations

17

Advancement in Machine Learning: A Strategic Lookout from Cancer Identification to Treatment DOI
Maitri Bhatt, Pravin Shende

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(4), P. 2777 - 2792

Published: Jan. 20, 2023

Language: Английский

Citations

10

From The Internet of Things (IoT) to The Internet of Behaviors (IoB) for Data Analysis DOI
Imane Moustati, Noreddine Gherabi, Hakim El Massari

et al.

Published: Dec. 16, 2023

The Internet of Behaviors (IoB), a relatively new research and development area, can be considered an ecosystem that blends technology, advanced data analysis, edge analytics, behavioral science, aims to aggregate, analyze comprehend, from the standpoint human psychology, users' gathered IoT devices online platforms. Then, utilize this comprehension alter or influence behavior. In paper, we provide up-to-date literature review explain $I o B$, its primary characteristics, connection DKIW pyramid. focus on IoB key-enablers technologies, summarize main application fields domains, describe challenges addressed by ecosystem.

Language: Английский

Citations

10

Machine Learning System for the Effective Diagnosis and Survival Prediction of Breast Cancer Patients DOI Open Access
Á Díaz Gago,

J.M. Aguirre,

Lenis Wong

et al.

International Journal of Online and Biomedical Engineering (iJOE), Journal Year: 2024, Volume and Issue: 20(02), P. 95 - 113

Published: Feb. 14, 2024

Breast cancer is one of the most significant global health challenges. Effective diagnosis and prognosis prediction are crucial for improving patient outcomes in case this disease. As machine learning (ML) has significantly improved models many disciplines, goal study to develop a ML system medical specialists that can accurately predict tumor survival breast patients. For training prediction, five algorithmic models—decision tree (DT), random forest (RF), naive bayes (NB), support vector machines (SVMs), gradient boosting—were trained with 569 records from Cancer Wisconsin dataset 1,980 Gene Expression Profiles dataset. The results showed NB model exhibited better performance diagnosis, achieving an accuracy 95.0%, while RF presented best survival, 76.0%. A survey experts’ experience resulting high scores reliability, performance, satisfaction, usability, efficiency, confirming systems have potential improve outcomes.

Language: Английский

Citations

3

A dynamic model using k-NN algorithm for predicting diabetes and breast cancer DOI Creative Commons
Hussein Al-Khamees, Nor Samsiah Sani,

Ahmed Sileh Gifal

et al.

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 192, P. 110276 - 110276

Published: May 13, 2025

Language: Английский

Citations

0

The Impact of Ontology on the Prediction of Cardiovascular Disease Compared to Machine Learning Algorithms DOI Open Access
Hakim El Massari, Noreddine Gherabi, Sajida Mhammedi

et al.

International Journal of Online and Biomedical Engineering (iJOE), Journal Year: 2022, Volume and Issue: 18(11), P. 143 - 157

Published: Aug. 31, 2022

Cardiovascular disease is one of the chronic diseases that on rise. The complications occur when cardiovascular not discovered early and correctly diagnosed at right time. Various machine learning approaches, including ontology-based Machine Learning techniques, have lately played an essential role in medical science by building automated system can identify heart illness. This paper compares reviews most prominent algorithms, as well classification. Random Forest, Logistic regression, Decision Tree, Naive Bayes, k-Nearest Neighbours, Artificial Neural Network, Support Vector were among classification methods explored. dataset used consists 70000 instances be downloaded from Kaggle website. findings are assessed using performance measures generated confusion matrix, such F-Measure, Accuracy, Recall, Precision. results showed ontology outperformed all algorithms.

Language: Английский

Citations

11

Prediction of breast cancer based on computer vision and artificial intelligence techniques DOI
Asif Irshad Khan, Yoosef B. Abushark, Fawaz Alsolami

et al.

Measurement, Journal Year: 2023, Volume and Issue: 218, P. 113230 - 113230

Published: June 24, 2023

Language: Английский

Citations

6

Road Accident Detection using SVM and Learning: A Comparative Study DOI Open Access
Fatima Qanouni, Hakim El Massari, Noreddine Gherabi

et al.

International Journal of Advanced Computer Science and Applications, Journal Year: 2024, Volume and Issue: 15(5)

Published: Jan. 1, 2024

Everyday, a great deal of children and young adults (aged five to 29) lives are lost in road accidents. The most frequent causes driver's behavior, the streets infrastructure is lower quality delayed response emergency services especially rural areas. There need for automatics accident systems detection that can assist recognizing accidents determining their positions. This work reviews existing machine learning approaches detection. We propose three distinct classifiers: Convolutional Neural Network CNN, Recurrent Convolution R-CNN Support Vector Machine SVM, using CCTV footage dataset. These models evaluated based on ROC curve, F1 measure, precision, accuracy recall, achieved accuracies were 92%, 82%, 93%, respectively. In addition, we suggest an ensemble strategy maximize strengths individual classifiers, raising 94%.

Language: Английский

Citations

2

An efficient ensemble-based Machine Learning for breast cancer detection DOI
Ramdas Kapila, Sumalatha Saleti

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 86, P. 105269 - 105269

Published: July 18, 2023

Language: Английский

Citations

5