Journal of Computer Science Research

Big Data 4.0: The Era of Big Intelligence

2023-11-15T10:01:14+08:00

Big data has had significant impacts on our lives, economies, academia and industries over the past decade. The current questions are: What is the future of big data? What era do we live in? This article addresses these questions by looking at meta as an operation and argues that we are living in the era of big intelligence through analyzing from meta (big data) to big intelligence. More specifically, this article will analyze big data from an evolutionary perspective. The article overviews data, information, knowledge, and intelligence (DIKI) and reveals their relationships. After analyzing meta as an operation, this article explores Meta (DIKE) and its relationship. It reveals 5 Bigs consisting of big data, big information, big knowledge, big intelligence and big analytics. Applying meta on 5 Bigs, this article infers that Big Data 4.0 = meta⁴ (big data) = big intelligence. This article analyzes how intelligent big analytics support big intelligence. The proposed approach in this research might facilitate the research and development of big data, big data analytics, business intelligence, artificial intelligence, and data science.

Machine Learning Prediction of Fetal Health Status from Cardiotocography Examination in Developing Healthcare Contexts

2024-01-30T20:19:23+08:00

Reducing neonatal mortality is a critical global health objective, especially in resource-constrained developing countries. This study employs machine learning (ML) techniques to predict fetal health status based on cardiotocography (CTG) examination findings, utilizing a dataset from the Kaggle repository due to the limited comprehensive healthcare data available in developing nations. Features such as baseline fetal heart rate, uterine contractions, and waveform characteristics were extracted using the RFE wrapper feature engineering technique and scaled with a standard scaler. Six ML models—Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), Categorical Boosting (CB), and Extended Gradient Boosting (XGB)—are trained via cross-validation and evaluated using performance metrics. The developed models were trained via cross-validation and evaluated using ML performance metrics. Eight out of the 21 features selected by GB returned their maximum Matthews Correlation Coefficient (MCC) score of 0.6255, while CB, with 20 of the 21 features, returned the maximum and highest MCC score of 0.6321. The study demonstrated the ability of ML models to predict fetal health conditions from CTG exam results, facilitating early identification of high-risk pregnancies and enabling prompt treatment to prevent severe neonatal outcomes.

Exploring Alternatives to Create Digital Twins from and for Process Simulation

2023-12-19T18:46:29+08:00

In this work, Digital Twins based on Neural Networks for the steady state production of styrene were generated. Thus, both the Aspen Technology AI Model Builder (alternative 1) and a homemade MS Excel VBA code connected to Aspen HYSYS and Aspen Plus (alternative 2) were used with this same aim. The raw data used for generating the Digital Twins were obtained from process simulations using Aspen HYSYS and/or Aspen Plus, which were connected through a recycle-like stream via automation for solving the entire simulation flowsheet. Aspen HYSYS was used for solving the pre-heating, reaction, and stabilization sections of the process whereas Aspen Plus ensured the computing of the separation and purification columns. Both alternatives led to an excellent prediction showing the capability of creating Digital Twins from and for process simulation.

On Enforcing Dyadic-type Homogeneous Binary Function Product Constraints in MatBase

2024-01-25T22:55:43+08:00

Homogeneous binary function products are often encountered in the sub-universes modeled by databases, from genealogical trees to sports, from education to healthcare, etc. Their properties must be discovered and enforced by the software applications managing such data to guarantee plausibility. The (Elementary) Mathematical Data Model provides 17 dyadic-type homogeneous binary function product constraint types. MatBase, an intelligent data and knowledge base management system prototype, allows database designers to simply declare them by only clicking corresponding checkboxes and automatically generates code for enforcing them. This paper describes the algorithms that MatBase uses for enforcing all these 17 homogeneous binary function product constraint types, which may also be used by developers not having access to MatBase.