This research aims to study and assess state-of-the-art physics-informed neural networks (PINNs) from different researchers’ perspectives. The PRISMA framework was used for a systematic literature review, and 120 research articles from the computational sciences and engineering domain were specifically classified through a well-defined keyword search in Scopus and Web of Science databases. Through bibliometric analyses, we have identified journal sources with the most publications, authors with high citations, and countries with many publications on PINNs. Some newly improved techniques developed to enhance PINN performance and reduce high training costs and slowness, among other limitations, have been highlighted. Different approaches have been introduced to overcome the limitations of PINNs. In this review, we categorized the newly proposed PINN methods into Extended PINNs, Hybrid PINNs, and Minimized Loss techniques. Various potential future research directions are outlined based on the limitations of the proposed solutions.

The Global Breast Cancer Initiative (GBCI) Framework, launched by the World Health Organisation (WHO) in 2023, emphasises assessing, strengthening, and scaling up services for the early detection and management of breast cancer. This study aims to determine the feasibility of monitoring the status of breast cancer control in the 21 Asian National Cancer Centers Alliance (ANCCA) countries based on the three GBCI Framework key performance indicators (KPIs): stage at diagnosis, time to diagnosis, and treatment completion. We reviewed published literature on breast cancer control among 21 ANCCA countries from May to July 2023 to establish data availability and compiled the latest descriptive statistics and sources of the indicators using a standardised data collection form. We performed bivariate Pearson's correlation analysis to measure the strength of correlation between stage at diagnosis, mortality and survival rates, and universal health coverage. Only 12 (57%) ANCCA member countries published national cancer registry reports on breast cancer age-standardised incidence rate (ASIR) and age-standardised mortality rate (ASMR). Indonesia, Myanmar, and Nepal had provincial data and others relied on WHO's Global Cancer Observatory (GLOBOCAN) estimates. GLOBOCAN data differed from the reported national statistics by 5-10% in Bhutan, Indonesia, Iran, the Republic of Korea, Singapore, and Thailand and >10% in China, India, Malaysia, Mongolia, and Sri Lanka. The proportion of patients diagnosed in stages I and II strongly correlated with the five-year survival rate and with the universal health coverage (UHC) index. Three countries (14%) reported national data with >60% of invasive breast cancer patients diagnosed at stages I and II, and a five-year survival rate of >80%. Over 60% of the ANCCA countries had no published national data on breast cancer staging, the time interval from presentation to diagnosis, and diagnosis to treatment. Five (24%) countries reported data on treatment completion. The definition of delayed diagnosis and treatment completion varied across countries. GBCI's Pillar 1 KPI correlates strongly with five-year survival rate and with the UHC index. Most ANCCA countries lacked national data on cancer staging, timely diagnosis, and treatment completion KPIs. While institutional-level data were available in some countries, they may not represent the nationwide status. Strengthening cancer surveillance is crucial for effective breast cancer control. The GBCI Framework indicators warrant more detailed definitions for standardised data collection. Surrogate indicators which are measurable and manageable in country-specific settings, could be considered for monitoring GBCI indicators. Ensuring UHC and addressing health inequalities are essential to early diagnosis and treatment of breast cancer. Funding for this research article's processing fee (APC) will be provided by the affiliated institution to support the open-access publication of this work. The funding body is not involved in the study design; collection, management, analysis and interpretation of data; or the decision to submit for publication. The funding body will be informed of any planned publications, and documentation provided.

Thermal maturity, organic richness and kerogen typing are very important parameters to be evaluated for source rock characterization. Due to the difficulties of high cost geochemical analyses and the unavailability of rock samples, it was necessary to examine and test many different method and techniques to help in the prediction of TOC values as well as other maturity indicators in case of missing or absence of geochemical data. Integrated study of machine learning techniques and well-log data has been applied on Cretaceous–Paleocene formations in the Taranaki Basin, New Zealand. A novel approach of maturity prediction using T_max and vitrinite reflectance (VR%) is the first and preliminary objective of this research. Moreover, the organic richness or the total organic carbon (TOC) content has been predicted as well. Geochemical and well-log data collected from the Cretaceous Rakopi and North Cape formations and Paleocene Mangahewa Formation have been processed and prepared to apply the machine learning techniques. Five machine learning techniques, namely Bayesian regularization for feed-forward neural networks (BRNNs), random forest (RF), support vector machine (SVM) for regression, linear regression (LR) and Gaussian process regression (GPR), were employed for prediction of TOC, T_max and VR, and their results have been compared. For TOC prediction, the best model achieved the coefficient of determination (R²) value of 0.964 using RF model. For T_max prediction, BRNN with one hidden layer achieved the R² value of 0.828. BRNN with two hidden layers produced the best model for VR prediction achieving R² = 0.636. A comparison of five ML techniques showed that all of these techniques performed exceedingly well for TOC prediction with a value of R² > 0.96. In contrast, BRNN with one hidden layer was the only ML technique able to achieve R² > 0.8 for T_max and BRNN with two hidden layers was the only ML technique able to achieve R² > 0.6 for VR prediction. Therefore, this research provides a strong empirical evidence that ML techniques can capture the nonlinear relationship between the well-log data and TOC as well as the maturity indicators which may not be fully understood by existing linear models.

This article provides a cross-sectional weighted measurement of noncommunicable diseases (NCDs) and risk factors prevalence among Brunei adult population using WHO STEPS methodology. A 2-staged randomized sampling was conducted during August 2015 to April 2016. Three-step surveillance included (1) interview using standardized questionnaire, (2) blood pressure and anthropometric measurements, and (3) biochemistry tests. Data weighting was applied. A total of 3808 adults aged 18 to 69 years participated in step 1; 2082 completed steps 2 and 3 measurements. Adult smoking prevalence was 19.9%, obesity 28.2%, hypertension 28.0%, diabetes 9.7%, prediabetes 2.1%, and 51.3% had fasting cholesterol level ≥5 mmol/L. Inadequate consumption of fruits and vegetables prevalence was high at 91.7%. Among those aged 40 to 69 years, 8.9% had a 10-year cardiovascular disease (CVD) risk ≥30%, or with existing CVD. Population strategies and targeted group interventions are required to control the NCD risk factors and morbidities.

The mix of native language with other languages (code-mixing) in social media has posed a severe challenge for language identification (LID) systems. It has encouraged research on code-mixed LID solutions. This study investigated the techniques, challenges, and dataset availability with corresponding quality criteria and developed a comprehensive framework for code-mixed LID. This study addressed four research issues to identify gaps and future work opportunities in tackling code-mixed LID challenges. Based on our analysis of reviewed studies, we outlined key points for future research in code-mixed LID. We demonstrated a taxonomy of applied techniques for code-mixed LID and highlighted the different technique variants. In code-mixed LID tasks, we discovered four significant challenges: ambiguity, lexical borrowing, non-standard words, and intra-word code-mixing. This systematic literature review recognised 32 code-mixed datasets available for LID. We proposed five features to describe the quality criteria dataset. The features are the number of instances or sentences, percentage of code-mixed types in the data, number of tokens, number of unique tokens, and average sentence length. Finally, we synthesised the methodologies and proposed a conceptual framework for subsequent studies through our literature analysis.