Implementation of Data Mining on a Secure Cloud Computing over a Web API using Supervised Machine Learning Algorithm

Ige, Tosin; Adewale, Sikiru

doi:10.14569/ijacsa.2022.0130501

Cited by 4 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It works by looking for a hyper-plane (Figure 3) that creates a boundary between two classes of data so as to properly classify them, it determines the best decision boundary between categories, hence they can be applied to vector which can encode data, and so text are classified into vector during text classification tasks by SVM algorithm. Once the algorithm determined the decision boundary for each of the category in the dataset for which we want to analyze, we can proceed to obtain the representations of each of all the texts we want to classify in our NLP [9][10][11][12] and check for the side of the boundary that those representations fall into.…”

Section: ) Support Vector Machine (Svm)mentioning

confidence: 99%

Evaluation and Comparison of SVM, Deep Learning, and Naïve Bayes Performances for Natural Language Processing Text Classification Task

Ogaga,

Olalere

2023

Preprint

View full text Add to dashboard Cite

Text classification is one of the most important task in natural language processing, In this research, we carried out several experimental research on three (3) of the most popular Text classification NLP classifier in Convolutional Neural Network (CNN), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVN). In the presence of enough training data, Deep Learning CNN works best in all parameters for evaluation with 77% accuracy, followed by SVM with accuracy of 76%, and multinomial Bayes with least performance of 69% accuracy. CNN has the best performance in the presence of large enough training dataset because of the presence of filter/ kernels which help to indentify patterns in text data regardless of their position in the sentence. We repeated the training again with just one-third of our data, at this point SVM comes with the best performance, the performance of CNN noticeably drops but still better than Multinomial Naive Bayes, the reason why SVM works best when we reduce the training data was because of its ability to look for a hyper-plane that creates a boundary between different classes of data so as to properly classify them, so we believed that getting the hyper-plane was more efficient when we reduce the dataset, hence reason for the good performance. Multinomial Naive Bayes have the least performance which we attributed to its assumption of independency between the features which sometimes does not hold true. We concluded that availability of data should be an important factor when choosing classifier for Natural Language Processing Text Classification task. CNN should be use in the presence of enough dataset, and SVM should be use when data is not enough. Multinomial Naive Bayes must not be trusted with state of the art NLP task due to its assumption of independency between the features.

show abstract

Section: ) Support Vector Machine (Svm)mentioning

confidence: 99%

Evaluation and Comparison of SVM, Deep Learning, and Naïve Bayes Performances for Natural Language Processing Text Classification Task

Ogaga,

Olalere

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…As the applications of AI in health care fall into the category of; Patient-oriented AI, Clinician-oriented AI, Administrative-and operational-oriented AI [5]. In the future, some of AI tasks could range from doing simplest of task to the most complex task which could be anything from receiving phone call to medical record review, population health trending and analytics, therapeutic drug and device design, reading radiology images, making clinical diagnoses and treatment plans, and even talking with patients.…”

Section: Future Prospects Of the Field As Ai Technologies In Healthcarementioning

confidence: 99%

The Rise of Artificial Intelligence and Machine Learning in HealthCare Industry

Ogaga,

Zhao

2023

IJRIAS

View full text Add to dashboard Cite

In this study, we examine some of the recent advancement in health care system as regards the rise of artificial intelligence. We analyzed background knowledge and review many literatures to examine some real world application of artificial intelligence for treatment, diagnoses, and prediction of diseases. As healthcare industries continues to embrace artificial intelligence to improve the quality of healthcare services, machine learning for prediction and diagnoses of treatment. All together, these create a new window of opportunities as well as challenges to overcome. We dived into how healthcare industry had been affected by the rise of AI technologies, what technologies are used and how they function, the limitations of AI technologies in healthcare, the future prospects of AI technologies in healthcare as it continue to advance and mature, and also the social and ethical implications of AI in healthcare system. There is clear evidence that continuous advancement of AI and machine learning will raise the operational efficiency of healthcare and its allied providers.

show abstract

“…Bioactive peptides bear structural analogies with natural protein motifs or endogenous regulatory peptides, thus making them suitable for genetic modulation; and enzymatic interactions associated with natural metabolic processes, nonetheless, in silico approaches and chemical syntheses are typically employed to comprehend the correlation between the structures and functions of specific models (Di Stefano et al, 2018). This reflects the extended use of collected data as means for proffering solutions for the modern man (Ige & Adewale, 2022a). Their biological activities requiring the inhibition of one or more digestive enzymes is seemingly common with trito hexapeptide chain lengths bearing a proline residue at minimal proximity to the C-terminal with an alanine or methionine at the Cterminal itself and either of arginine, lysine, threonine, tyrosine, or seine occupying the N-terminal position (Ibrahim et al, 2018).…”

Section: Antid Iab E Ti C and Anti Oxidative Mechanis Ms Of S Prouted...mentioning

confidence: 99%

Isolation of bioactive peptides and multiple nutraceuticals of antidiabetic and antioxidant functionalities through sprouting: Recent advances

Kehinde

Majid

Hussain³

2022

Journal of Food Biochemistry

View full text Add to dashboard Cite

The employment of proteases directly from enzymes or indirectly from microorganisms during fermentation for the purpose of proteolysis of food proteins has been the conventional trend for the derivation of bioactive peptides from food matrices. However, recent studies have shown that inherent protease enzymes can be activated for this activity for vegetable foods using the sprouting process. The benefits of ease of operation, and reduced processing costs are formidable advantages for the optimal consideration of this technique. On another note, the demand for functional foods with therapeutic health effects has increased in recent years. Globally, plant foods are perceived as dietetic choices bearing sufficient quantities of concomitant nutraceuticals. In this manuscript, the sprouting route for the isolation of peptides and glucosinolates, and for the enhancement of total phenolic contents, polyunsaturated fatty acid profiles, and other bioactive constituents was explored. Advances regarding the phytochemical transformations in the course of sprouting, the therapeutic functionalities, and microbiological safety concerns of vegetable sprouts are delineated. In addition, consumption of vegetable sprouts has been shown to be more efficient in supplying nutraceutical components relative to their unsprouted counterparts. Biochemical mechanisms involving the inhibition of digestive enzymes such as α‐amylase, β‐glucosidase, and dipeptidyl peptidase IV (DPP‐IV), single electron transfer, and metal chelation, for impartation of health benefits, have been reported to occur from bioactive components isolated from vegetable sprouts. Practical applications Sprouting initiates proteolysis of vegetable proteins for the release of bioactive peptides. Abiotic stresses can be used as elicitors during the sprouting process to achieve enhanced phytochemical profiles of sprouts. Sprouting is a relatively more convenient approach to the improvement of the health benefits of vegetable foods. Vegetable sprouts are potential for the management of metabolic syndrome disorders.

show abstract

Implementation of Data Mining on a Secure Cloud Computing over a Web API using Supervised Machine Learning Algorithm

Cited by 4 publications

References 7 publications

Evaluation and Comparison of SVM, Deep Learning, and Naïve Bayes Performances for Natural Language Processing Text Classification Task

Evaluation and Comparison of SVM, Deep Learning, and Naïve Bayes Performances for Natural Language Processing Text Classification Task

The Rise of Artificial Intelligence and Machine Learning in HealthCare Industry

Isolation of bioactive peptides and multiple nutraceuticals of antidiabetic and antioxidant functionalities through sprouting: Recent advances

Contact Info

Product

Resources

About