Front Cover
Publication Month: January 2024, Page(s): A1 – A1
Editorial Board
Publication Month: January 2024, Page(s): B1 – B1
Editorial
Publication Month: January 2024, Page(s): C1 – C1
Table of Contents
Publication Month: January 2024, Page(s): D1 – D1
NNR Artificial Intelligence Model in Azure for Bearing Prediction and Analysis
Henry Ogbemudia Omoregbee, Mabel Usunobun Olanipekun, Bright Aghogho Edward
J. Engg. Res. & Sci. 2(6), 1-9 (2023);
Neural Network regression (NNR) is considered more effective as compared to multiple neural networks model readily available in Azure to evaluate the Remaining Useful Life (RUL) of bearing in this work because it performs better than other models when used and was demonstrated as a non-programing technique for analyzing enormous data without the use of Hive, Hadoop, Pig, etc. To complement the earlier paper, we further used statistical means in verifying our results. Using this non-parametric non-linear approach is intuitively appealing to forecast the Remaining Useful Life (RUL) of a bearing. Over the years the Azure cloud service platform has gained recognition as a major forecasting technique toolbox of forecasters, NNR model implementations have surged, hence its inclusion here on its’ use on the NASA FEMTO-ST Institute (Franche-Comté ÉlectroniqueMécaniqueThermique et Optique – Sciences et Technologies) bearing dataset. Azure is a machine learning platform from Microsoft that allows developers to write, test, and deploy algorithms and has been motivationally proven adequate and useful for predicting the RUL of bearings. As seen in so many recent articles, NNR Artificial Intelligence is a model among many others readily available for computing on the platform that has been successfully used for non-programming of the enormous dataset and applied for forecasting the RUL of Bearing. This has added value in the forecasting phase. The novelty in this work is related to the application of NNR where we were able to combine the Dickey-Fuller Test with NNR to ensure that the data needed to be used with NNR is fit for application to yield optimal prediction results and our previous result from the past paper was further established. A satisfactory judgmental result was obtained; making Azure’s work studio a reasonable place to predict without much programming expertise. We tested the findings from the National Aeronautics and Space Administration (NASA) database for the person that came first in the competition by comparing our Azure model observations with the NNR observations collected. Ultimately, we showed the finding is enhanced by the AZURE model.
Imputation and Hyperparameter Optimization in Cancer Diagnosis
Yi Liu, Wendy Wang, Haibo Wang
J. Engg. Res. & Sci. 2(8), 1-18 (2023);
Cancer is one of the leading causes for death worldwide. Accurate and timely detection of cancer can save lives. As more machine learning algorithms and approaches have been applied in cancer diagnosis, there has been a need to analyze their performance. This study has compared the detection accuracy and speed of nineteen machine learning algorithms using a cervical cancer dataset. To make the approach general enough to detect various types of cancers, this study has intentionally excluded feature selection, a feature commonly applied in most studies for a specific dataset or a certain type of cancer. In addition, imputation and hyperparameter optimization have been employed to improve the algorithms’ performance. The results suggest that when both imputation and hyperparameter optimization are applied, the algorithms tend to perform better than when either of them is employed individually or when both are absent. The majority of the algorithms have shown improved accuracy in diagnosis, although with the trade-off of increased execution time. The findings from this study demonstrate the potential of machine learning in cancer diagnosis, especially the possibility of developing versatile systems that are able to detect various types of cancers with satisfactory performance.
A Swarm-Based Clinical Validation Framework of Artificial Intelligence Solutions for Non-Communicable Diseases
Kitty Kioskli, Spyridon Papastergiou, Theofanis Fotis
J. Engg. Res. & Sci. 2(9), 1-11 (2023);
Non-communicable diseases (NCDs) present complex challenges in patient care. Artificial Intelligence (AI) offers transformative potential, but its implementation requires addressing key issues. This study proposes a swarm intelligence-inspired clinical validation framework for NCDs, promoting openness, trustworthiness, and continuous self-validation. The framework creates a collaborative environment, connecting healthcare entities, patients, caregivers, and professionals. The swarm-based approach enhances diagnostic accuracy, enables personalized treatment, improves prognosis, supports clinical decision-making, engages patients, enables real-time monitoring, and promotes continuous learning. These implications have the power to revolutionize NCD management and improve patient outcomes.
Device Authentication using Homomorphic Encryption
Supriya Yadav, Gareth Howells
J. Engg. Res. & Sci. 2(10), 1-8 (2023);
In the digital era, data security in files, databases, accounts, and networks is of utmost importance. Due to the sensitive, private, or protected information they contain, databases are a common target for cyber attacks. To assess threats to data and lower the risk involved with data processing and storage, data security is crucial. Therefore, it is necessary to find solutions to the data security problems. It has become crucial to be up-to-date on different encryption technologies and trends due to the internet’s growing sophistication and dependence on internet data transmission. It can help protect confidential information and sensitive data and enhance the security of the system. In this paper, we propose a homomorphic encryption-based device authentication method while safeguarding template data. Homomorphic encryption technology has the capability of computing on encrypted data, making it more difficult for attackers to get their hands on the original template. In this study, the CKKS technique was used, which supports the approximation of real or complex numbers.
