Displaying publications 61 - 80 of 258 in total

Abstract:
Sort:
  1. Zaini N, Ean LW, Ahmed AN, Malek MA
    Environ Sci Pollut Res Int, 2022 Jan;29(4):4958-4990.
    PMID: 34807385 DOI: 10.1007/s11356-021-17442-1
    Rapid progress of industrial development, urbanization and traffic has caused air quality reduction that negatively affects human health and environmental sustainability, especially among developed countries. Numerous studies on the development of air quality forecasting model using machine learning have been conducted to control air pollution. As such, there are significant numbers of reviews on the application of machine learning in air quality forecasting. Shallow architectures of machine learning exhibit several limitations and yield lower forecasting accuracy than deep learning architecture. Deep learning is a new technology in computational intelligence; thus, its application in air quality forecasting is still limited. This study aims to investigate the deep learning applications in time series air quality forecasting. Owing to this, literature search is conducted thoroughly from all scientific databases to avoid unnecessary clutter. This study summarizes and discusses different types of deep learning algorithms applied in air quality forecasting, including the theoretical backgrounds, hyperparameters, applications and limitations. Hybrid deep learning with data decomposition, optimization algorithm and spatiotemporal models are also presented to highlight those techniques' effectiveness in tackling the drawbacks of individual deep learning models. It is clearly stated that hybrid deep learning was able to forecast future air quality with higher accuracy than individual models. At the end of the study, some possible research directions are suggested for future model development. The main objective of this review study is to provide a comprehensive literature summary of deep learning applications in time series air quality forecasting that may benefit interested researchers for subsequent research.
    Matched MeSH terms: Forecasting
  2. Cheng HS, Tan SP, Wong DMK, Koo WLY, Wong SH, Tan NS
    Int J Mol Sci, 2023 Mar 15;24(6).
    PMID: 36982702 DOI: 10.3390/ijms24065633
    Blood is conventionally thought to be sterile. However, emerging evidence on the blood microbiome has started to challenge this notion. Recent reports have revealed the presence of genetic materials of microbes or pathogens in the blood circulation, leading to the conceptualization of a blood microbiome that is vital for physical wellbeing. Dysbiosis of the blood microbial profile has been implicated in a wide range of health conditions. Our review aims to consolidate recent findings about the blood microbiome in human health and to highlight the existing controversies, prospects, and challenges around this topic. Current evidence does not seem to support the presence of a core healthy blood microbiome. Common microbial taxa have been identified in some diseases, for instance, Legionella and Devosia in kidney impairment, Bacteroides in cirrhosis, Escherichia/Shigella and Staphylococcus in inflammatory diseases, and Janthinobacterium in mood disorders. While the presence of culturable blood microbes remains debatable, their genetic materials in the blood could potentially be exploited to improve precision medicine for cancers, pregnancy-related complications, and asthma by augmenting patient stratification. Key controversies in blood microbiome research are the susceptibility of low-biomass samples to exogenous contamination and undetermined microbial viability from NGS-based microbial profiling, however, ongoing initiatives are attempting to mitigate these issues. We also envisage future blood microbiome research to adopt more robust and standardized approaches, to delve into the origins of these multibiome genetic materials and to focus on host-microbe interactions through the elaboration of causative and mechanistic relationships with the aid of more accurate and powerful analytical tools.
    Matched MeSH terms: Forecasting
  3. Wan Mohamad Nawi WIA, K Abdul Hamid AA, Lola MS, Zakaria S, Aruchunan E, Gobithaasan RU, et al.
    PLoS One, 2023;18(5):e0285407.
    PMID: 37172040 DOI: 10.1371/journal.pone.0285407
    Improving forecasting particularly time series forecasting accuracy, efficiency and precisely become crucial for the authorities to forecast, monitor, and prevent the COVID-19 cases so that its spread can be controlled more effectively. However, the results obtained from prediction models are inaccurate, imprecise as well as inefficient due to linear and non-linear patterns exist in the data set, respectively. Therefore, to produce more accurate and efficient COVID-19 prediction value that is closer to the true COVID-19 value, a hybrid approach has been implemented. Thus, aims of this study is (1) to propose a hybrid ARIMA-SVM model to produce better forecasting results. (2) to investigate in terms of the performance of the proposed models and percentage improvement against ARIMA and SVM models. statistical measurements such as MSE, RMSE, MAE, and MAPE then conducted to verify that the proposed models are better than ARIMA and SVM models. Empirical results with three real datasets of well-known cases of COVID-19 in Malaysia show that, compared to the ARIMA and SVM models, the proposed model generates the smallest MSE, RMSE, MAE and MAPE values for the training and testing datasets, means that the predicted value from the proposed model is closer to the actual value. These results prove that the proposed model can generate estimated values more accurately and efficiently. As compared to ARIMA and SVM, our proposed models perform much better in terms of error reduction percentages for all datasets. This is demonstrated by the maximum scores of 73.12%, 74.6%, 90.38%, and 68.99% in the MAE, MAPE, MSE, and RMSE, respectively. Therefore, the proposed model can be the best and effective way to improve prediction performance with a higher level of accuracy and efficiency in predicting cases of COVID-19.
    Matched MeSH terms: Forecasting
  4. Schumacher-Schuh AF, Bieger A, Okunoye O, Mok KY, Lim SY, Bardien S, et al.
    Mov Disord, 2022 Aug;37(8):1593-1604.
    PMID: 35867623 DOI: 10.1002/mds.29126
    BACKGROUND: Human genetics research lacks diversity; over 80% of genome-wide association studies have been conducted on individuals of European ancestry. In addition to limiting insights regarding disease mechanisms, disproportionate representation can create disparities preventing equitable implementation of personalized medicine.

    OBJECTIVE: This systematic review provides an overview of research involving Parkinson's disease (PD) genetics in underrepresented populations (URP) and sets a baseline to measure the future impact of current efforts in those populations.

    METHODS: We searched PubMed and EMBASE until October 2021 using search strings for "PD," "genetics," the main "URP," and and the countries in Latin America, Caribbean, Africa, Asia, and Oceania (excluding Australia and New Zealand). Inclusion criteria were original studies, written in English, reporting genetic results on PD from non-European populations. Two levels of independent reviewers identified and extracted information.

    RESULTS: We observed imbalances in PD genetic studies among URPs. Asian participants from Greater China were described in the majority of the articles published (57%), but other populations were less well studied; for example, Blacks were represented in just 4.0% of the publications. Also, although idiopathic PD was more studied than monogenic forms of the disease, most studies analyzed a limited number of genetic variants. We identified just nine studies using a genome-wide approach published up to 2021, including URPs.

    CONCLUSION: This review provides insight into the significant lack of population diversity in PD research highlighting the immediate need for better representation. The Global Parkinson's Genetics Program (GP2) and similar initiatives aim to impact research in URPs, and the early metrics presented here can be used to measure progress in the field of PD genetics in the future. © 2022 International Parkinson and Movement Disorder Society.

    Matched MeSH terms: Forecasting
  5. Yang S, Li X, Jiang Z, Xiao M
    PLoS One, 2023;18(10):e0290126.
    PMID: 37844110 DOI: 10.1371/journal.pone.0290126
    Based on the data of the Chinese A-share listed firms in China Shanghai and Shenzhen Stock Exchange from 2014 to 2021, this article explores the relationship between common institutional investors and the quality of management earnings forecasts. The study used the multiple linear regression model and empirically found that common institutional investors positively impact the precision of earnings forecasts. This article also uses graph neural networks to predict the precision of earnings forecasts. Our findings have shown that common institutional investors form external supervision over restricting management to release a wide width of earnings forecasts, which helps to improve the risk warning function of earnings forecasts and promote the sustainable development of information disclosure from management in the Chinese capital market. One of the marginal contributions of this paper is that it enriches the literature related to the economic consequences of common institutional shareholding. Then, the neural network method used to predict the quality of management forecasts enhances the research method of institutional investors and the behavior of management earnings forecasts. Thirdly, this paper calls for strengthening information sharing and circulation among institutional investors to reduce information asymmetry between investors and management.
    Matched MeSH terms: Forecasting
  6. Boo KBW, El-Shafie A, Othman F, Khan MMH, Birima AH, Ahmed AN
    Water Res, 2024 Mar 15;252:121249.
    PMID: 38330715 DOI: 10.1016/j.watres.2024.121249
    Groundwater, the world's most abundant source of freshwater, is rapidly depleting in many regions due to a variety of factors. Accurate forecasting of groundwater level (GWL) is essential for effective management of this vital resource, but it remains a complex and challenging task. In recent years, there has been a notable increase in the use of machine learning (ML) techniques to model GWL, with many studies reporting exceptional results. In this paper, we present a comprehensive review of 142 relevant articles indexed by the Web of Science from 2017 to 2023, focusing on key ML models, including artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), support vector regression (SVR), evolutionary computing (EC), deep learning (DL), ensemble learning (EN), and hybrid-modeling (HM). We also discussed key modeling concepts such as dataset size, data splitting, input variable selection, forecasting time-step, performance metrics (PM), study zones, and aquifers, highlighting best practices for optimal GWL forecasting with ML. This review provides valuable insights and recommendations for researchers and water management agencies working in the field of groundwater management and hydrology.
    Matched MeSH terms: Forecasting
  7. Chan Phooi M'ng J, Mehralizadeh M
    PLoS One, 2016;11(6):e0156338.
    PMID: 27248692 DOI: 10.1371/journal.pone.0156338
    The motivation behind this research is to innovatively combine new methods like wavelet, principal component analysis (PCA), and artificial neural network (ANN) approaches to analyze trade in today's increasingly difficult and volatile financial futures markets. The main focus of this study is to facilitate forecasting by using an enhanced denoising process on market data, taken as a multivariate signal, in order to deduct the same noise from the open-high-low-close signal of a market. This research offers evidence on the predictive ability and the profitability of abnormal returns of a new hybrid forecasting model using Wavelet-PCA denoising and ANN (named WPCA-NN) on futures contracts of Hong Kong's Hang Seng futures, Japan's NIKKEI 225 futures, Singapore's MSCI futures, South Korea's KOSPI 200 futures, and Taiwan's TAIEX futures from 2005 to 2014. Using a host of technical analysis indicators consisting of RSI, MACD, MACD Signal, Stochastic Fast %K, Stochastic Slow %K, Stochastic %D, and Ultimate Oscillator, empirical results show that the annual mean returns of WPCA-NN are more than the threshold buy-and-hold for the validation, test, and evaluation periods; this is inconsistent with the traditional random walk hypothesis, which insists that mechanical rules cannot outperform the threshold buy-and-hold. The findings, however, are consistent with literature that advocates technical analysis.
    Matched MeSH terms: Forecasting
  8. Tariq MU, Ismail SB
    PLoS One, 2024;19(3):e0294289.
    PMID: 38483948 DOI: 10.1371/journal.pone.0294289
    The COVID-19 pandemic has had a significant impact on both the United Arab Emirates (UAE) and Malaysia, emphasizing the importance of developing accurate and reliable forecasting mechanisms to guide public health responses and policies. In this study, we compared several cutting-edge deep learning models, including Long Short-Term Memory (LSTM), bidirectional LSTM, Convolutional Neural Networks (CNN), hybrid CNN-LSTM, Multilayer Perceptron's, and Recurrent Neural Networks (RNN), to project COVID-19 cases in the aforementioned regions. These models were calibrated and evaluated using a comprehensive dataset that includes confirmed case counts, demographic data, and relevant socioeconomic factors. To enhance the performance of these models, Bayesian optimization techniques were employed. Subsequently, the models were re-evaluated to compare their effectiveness. Analytic approaches, both predictive and retrospective in nature, were used to interpret the data. Our primary objective was to determine the most effective model for predicting COVID-19 cases in the United Arab Emirates (UAE) and Malaysia. The findings indicate that the selected deep learning algorithms were proficient in forecasting COVID-19 cases, although their efficacy varied across different models. After a thorough evaluation, the model architectures most suitable for the specific conditions in the UAE and Malaysia were identified. Our study contributes significantly to the ongoing efforts to combat the COVID-19 pandemic, providing crucial insights into the application of sophisticated deep learning algorithms for the precise and timely forecasting of COVID-19 cases. These insights hold substantial value for shaping public health strategies, enabling authorities to develop targeted and evidence-based interventions to manage the virus spread and its impact on the populations of the UAE and Malaysia. The study confirms the usefulness of deep learning methodologies in efficiently processing complex datasets and generating reliable projections, a skill of great importance in healthcare and professional settings.
    Matched MeSH terms: Forecasting
  9. Ismail AM, Ab Hamid SH, Abdul Sani A, Mohd Daud NN
    PLoS One, 2024;19(4):e0299585.
    PMID: 38603718 DOI: 10.1371/journal.pone.0299585
    The performance of the defect prediction model by using balanced and imbalanced datasets makes a big impact on the discovery of future defects. Current resampling techniques only address the imbalanced datasets without taking into consideration redundancy and noise inherent to the imbalanced datasets. To address the imbalance issue, we propose Kernel Crossover Oversampling (KCO), an oversampling technique based on kernel analysis and crossover interpolation. Specifically, the proposed technique aims to generate balanced datasets by increasing data diversity in order to reduce redundancy and noise. KCO first represents multidimensional features into two-dimensional features by employing Kernel Principal Component Analysis (KPCA). KCO then divides the plotted data distribution by deploying spectral clustering to select the best region for interpolation. Lastly, KCO generates the new defect data by interpolating different data templates within the selected data clusters. According to the prediction evaluation conducted, KCO consistently produced F-scores ranging from 21% to 63% across six datasets, on average. According to the experimental results presented in this study, KCO provides more effective prediction performance than other baseline techniques. The experimental results show that KCO within project and cross project predictions especially consistently achieve higher performance of F-score results.
    Matched MeSH terms: Forecasting
  10. Butt UM, Letchmunan S, Hassan FH, Koh TW
    PLoS One, 2022;17(9):e0274172.
    PMID: 36070317 DOI: 10.1371/journal.pone.0274172
    The continued urbanization poses several challenges for law enforcement agencies to ensure a safe and secure environment. Countries are spending a substantial amount of their budgets to control and prevent crime. However, limited efforts have been made in the crime prediction area due to the deficiency of spatiotemporal crime data. Several machine learning, deep learning, and time series analysis techniques are exploited, but accuracy issues prevail. Thus, this study proposed a Bidirectional Long Short Term Memory (Bi-LSTM) and Exponential Smoothing (ES) hybrid for crime forecasting. The proposed technique is evaluated using New York City crime data from 2010-2017. The proposed approach outperformed as compared to state-of-the-art Seasonal Autoregressive Integrated Moving Averages (SARIMA) with low Mean Absolute Percentage Error (MAPE) (0.3738, 0.3891, 0.3433,0.3964), Root Mean Square Error (RMSE)(13.146, 13.669, 13.104, 13.77), and Mean Absolute Error (MAE) (9.837, 10.896, 10.598, 10.721). Therefore, the proposed technique can help law enforcement agencies to prevent and control crime by forecasting crime patterns.
    Matched MeSH terms: Forecasting
  11. Romanello M, McGushin A, Di Napoli C, Drummond P, Hughes N, Jamart L, et al.
    Lancet, 2021 Oct 30;398(10311):1619-1662.
    PMID: 34687662 DOI: 10.1016/S0140-6736(21)01787-6
    The Lancet Countdown is an international collaboration that independently monitors the health consequences of a changing climate. Publishing updated, new, and improved indicators each year, the Lancet Countdown represents the consensus of leading researchers from 43 academic institutions and UN agencies. The 44 indicators of this report expose an unabated rise in the health impacts of climate change and the current health consequences of the delayed and inconsistent response of countries around the globe—providing a clear imperative for accelerated action that puts the health of people and planet above all else. The 2021 report coincides with the UN Framework Convention on Climate Change 26th Conference of the Parties (COP26), at which countries are facing pressure to realise the ambition of the Paris Agreement to keep the global average temperature rise to 1·5°C and to mobilise the financial resources required for all countries to have an effective climate response. These negotiations unfold in the context of the COVID-19 pandemic—a global health crisis that has claimed millions of lives, affected livelihoods and communities around the globe, and exposed deep fissures and inequities in the world’s capacity to cope with, and respond to, health emergencies. Yet, in its response to both crises, the world is faced with an unprecedented opportunity to ensure a healthy future for all.

    DEEPENING INEQUITIES IN A WARMING WORLD: Record temperatures in 2020 resulted in a new high of 3·1 billion more person-days of heatwave exposure among people older than 65 years and 626 million more person-days affecting children younger than 1 year, compared with the annual average for the 1986–2005 baseline (indicator 1.1.2). Looking to 2021, people older than 65 years or younger than 1 year, along with people facing social disadvantages, were the most affected by the record-breaking temperatures of over 40°C in the Pacific Northwest areas of the USA and Canada in June, 2021—an event that would have been almost impossible without human-caused climate change. Although the exact number will not be known for several months, hundreds of people have died prematurely from the heat. Furthermore, populations in countries with low and medium levels of UN-defined human development index (HDI) have had the biggest increase in heat vulnerability during the past 30 years, with risks to their health further exacerbated by the low availability of cooling mechanisms and urban green space (indicators 1.1.1, 2.3.2, and 2.3.3). Agricultural workers in countries with low and medium HDI were among the worst affected by exposure to extreme temperatures, bearing almost half of the 295 billion potential work hours lost due to heat in 2020 (indicator 1.1.4). These lost work hours could have devastating economic consequences to these already vulnerable workers—data in this year’s report shows that the average potential earnings lost in countries in the low HDI group were equivalent to 4–8% of the national gross domestic product (indicator 4.1.3). Through these effects, rising average temperatures, and altered rainfall patterns, climate change is beginning to reverse years of progress in tackling the food and water insecurity that still affects the most underserved populations around the world, denying them an essential aspect of good health. During any given month in 2020, up to 19% of the global land surface was affected by extreme drought; a value that had not exceeded 13% between 1950 and 1999 (indicator 1.2.2). In parallel with drought, warm temperatures are affecting the yield potential of the world’s major staple crops—a 6·0% reduction for maize; 3·0% for winter wheat; 5·4% for soybean; and 1·8% for rice in 2020, relative to 1981–2010 (indicator 1.4.1)—exposing the rising risk of food insecurity. Adding to these health hazards, the changing environmental conditions are also increasing the suitability for the transmission of many water-borne, air-borne, food-borne, and vector-borne pathogens. Although socioeconomic development, public health interventions, and advances in medicine have reduced the global burden of infectious disease transmission, climate change could undermine eradication efforts. The number of months with environmentally suitable conditions for the transmission of malaria (Plasmodium falciparum) rose by 39% from 1950–59 to 2010–19 in densely populated highland areas in the low HDI group, threatening highly disadvantaged populations who were comparatively safer from this disease than those in the lowland areas (indicator 1.3.1). The epidemic potential for dengue virus, Zika virus, and chikungunya virus, which currently primarily affect populations in central America, South America, the Caribbean, Africa, and south Asia, increased globally, with a basic reproductive rate increase of 13% for transmission by Aedes aegypti and 7% for transmission by Aedes albopictus compared with the 1950s. The biggest relative increase in basic reproductive rate of these arboviruses was seen in countries in the very high HDI group (indicator 1.3.1); however, people in the low HDI group are confronted with the highest vulnerability to these arboviruses (indicator 1.3.2). Similar findings are observed in the environmental suitability for Vibrio cholerae, a pathogen estimated to cause almost 100 000 deaths annually, particularly among populations with poor access to safe water and sanitation. Between 2003 and 2019, the coastal areas suitable for V cholerae transmission increased substantially across all HDI country groups—although, with 98% of their coastline suitable to the transmission of V cholerae in 2020, it is people in the low HDI country group that have the highest environmental suitability for this disease (indicator 1.3.1). The concurrent and interconnecting risks posed by extreme weather events, infectious disease transmission, and food, water, and financial insecurity are over-burdening the most vulnerable populations. Through multiple simultaneous and interacting health risks, climate change is threatening to reverse years of progress in public health and sustainable development. Even with overwhelming evidence on the health impacts of climate change, countries are not delivering an adaptation response proportionate to the rising risks their populations face. In 2020, 104 (63%) of 166 countries did not have a high level of implementation of national health emergency frameworks, leaving them unprepared to respond to pandemics and climate-related health emergencies (indicator 2.3.1). Importantly, only 18 (55%) of 33 countries with a low HDI had reported at least a medium level of implementation of national health emergency frameworks, compared with 47 (89%) of 53 countries with a very high HDI. In addition, only 47 (52%) of 91 countries reported having a national adaptation plan for health, with insufficient human and financial resources identified as the main barrier for their implementation (indicator 2.1.1). With a world facing an unavoidable temperature rise, even with the most ambitious climate change mitigation, accelerated adaptation is essential to reduce the vulnerabilities of populations to climate change and protect the health of people around the world.

    AN INEQUITABLE RESPONSE FAILS EVERYONE: 10 months into 2021, global and equitable access to the COVID-19 vaccine had not been delivered—more than 60% of people in high-income countries have received at least one dose of a COVID-19 vaccine compared with just 3·5% of people in low-income countries. Data in this report exposes similar inequities in the global climate change mitigation response. To meet the Paris Agreement goals and prevent catastrophic levels of global warming, global greenhouse gas emissions must reduce by half within a decade. However, at the current pace of reduction, it would take more than 150 years for the energy system to fully decarbonise (indicator 3.1), and the unequal response between countries is resulting in an uneven realisation of the health benefits of a low-carbon transition. The use of public funds to subsidise fossil fuels is partly responsible for the slow decarbonisation rate. Of the 84 countries reviewed, 65 were still providing an overall subsidy to fossil fuels in 2018 and, in many cases, subsidies were equivalent to substantial proportions of the national health budget and could have been redirected to deliver net benefits to health and wellbeing. Furthermore, all the 19 countries whose carbon pricing policies outweighed the effect of any fossil fuels subsidies came from the very high HDI group (indicator 4.2.4). Although countries in the very high HDI group have collectively made the most progress in the decarbonisation of the energy system, they are still the main contributors to CO2 emissions through the local production of goods and services, accounting for 45% of the global total (indicator 4.2.5). With a slower pace of decarbonisation and poorer air quality regulations than countries in the very high HDI group, the medium and high HDI country groups produce the most fine particle matter (PM2·5) emissions and have the highest rates of air pollution-related deaths, which are about 50% higher than the total deaths in the very high HDI group (indicator 3.3). The low HDI group, with comparatively lower amounts of industrial activity than in the other groups, has a local production that contributes to only 0·7% of global CO2 emissions, and has the lowest mortality rate from ambient air pollution. However, with only 12% of its inhabitants relying on clean fuels and technologies for cooking, the health of these populations is still at risk from dangerously high concentrations of household air pollution (indicator 3.2). Even in the most affluent countries, people in the most deprived areas over-whelmingly bear the burden of health effects from exposure to air pollution. These findings expose the health costs of the delayed and unequal mitigation response and underscore the millions of deaths to be prevented annually through a low-carbon transition that prioritises the health of all populations. However, the world is not on track to realising the health gains of the transition to a low-carbon economy. Current global decarbonisation commitments are insufficient to meet Paris Agreement ambitions and would lead to a roughly 2·4°C average global temperature increase by the end of the century. The current direction of post-COVID-19 spending is threatening to make this situation worse, with just 18% of all the funds committed for economic recovery from the COVID-19 pandemic by the end of 2020 expected to lead to a reduction of greenhouse gas emissions. Indeed, the economic recovery from the pandemic is already predicted to lead to an unprecedented 5% increase in greenhouse gas emissions in 2021, which will bring global anthropogenic emissions back to their peak amounts. In addition, the current economic recession is threatening to undermine the target of mobilising US$100 billion per year from 2020 onwards to promote low-carbon shifts and adaptation responses in the most underserved countries, even though this quantity is minute compared with the trillions allocated to COVID-19 recovery. The high amounts of borrowing that countries have had to resort to during the pandemic could erase their ability to deliver a green recovery and maximise the health gains to their population of a low-carbon transition.

    AN UNPRECEDENTED OPPORTUNITY TO ENSURE A HEALTHY FUTURE FOR ALL: The overshoot in emissions resulting from a carbon-intensive COVID-19 recovery would irreversibly prevent the world from meeting climate commitments and the Sustainable Development Goals and lock humanity into an increasingly extreme and unpredictable environment. Data in this report expose the health impacts and health inequities of the current world at 1·2°C of warming above pre-industrial levels and supports that, on the current trajectory, climate change will become the defining narrative of human health. However, by directing the trillions of dollars that will be committed to COVID-19 recovery towards the WHO’s prescriptions for a healthy, green recovery, the world could meet the Paris Agreement goals, protect the natural systems that support wellbeing, and minimise inequities through reduced health effects and maximised co-benefits of a universal low-carbon transition. Promoting equitable climate change mitigation and universal access to clean energies could prevent millions of deaths annually from reduced exposure to air pollution, healthier diets, and more active lifestyles, and contribute to reducing health inequities globally. This pivotal moment of economic stimulus represents a historical opportunity to secure the health of present and future generations. There is a glimpse of positive change through several promising trends in this year’s data: electricity generation from renewable wind and solar energy increased by an annual average of 17% between 2013 and 2018 (indicator 3.1); investment in new coal capacity decreased by 10% in 2020 (indicator 4.2.1); and the global number of electric vehicles reached 7·2 million in 2019 (indicator 3.4). Additionally, the global pandemic has driven increased engagement in health and climate change across multiple domains in society, with 91 heads of state making the connection in the 2020 UN General Debate and newly widespread engagement among countries in the very high HDI group (indicator 5.4). Whether COVID-19 recovery supports, or reverses these trends, is yet to be seen. Neither COVID-19 nor climate change respect national borders. Without widespread, accessible vaccination across all countries and societies, SARS-CoV-2 and its new variants will continue to put the health of everybody at risk. Likewise, tackling climate change requires all countries to deliver an urgent and coordinated response, with COVID-19 recovery funds allocated to support and ensure a just transition to a low-carbon future and climate change adaptation across the globe. Leaders of the world have an unprecedented opportunity to deliver a future of improved health, reduced inequity, and economic and environmental sustainability. However, this will only be possible if the world acts together to ensure that no person is left behind.

    Matched MeSH terms: Forecasting
  12. Noor Rodi NS, Malek MA, Ismail AR, Ting SC, Tang CW
    Water Sci Technol, 2014;70(10):1641-7.
    PMID: 25429452 DOI: 10.2166/wst.2014.420
    This study applies the clonal selection algorithm (CSA) in an artificial immune system (AIS) as an alternative method to predicting future rainfall data. The stochastic and the artificial neural network techniques are commonly used in hydrology. However, in this study a novel technique for forecasting rainfall was established. Results from this study have proven that the theory of biological immune systems could be technically applied to time series data. Biological immune systems are nonlinear and chaotic in nature similar to the daily rainfall data. This study discovered that the proposed CSA was able to predict the daily rainfall data with an accuracy of 90% during the model training stage. In the testing stage, the results showed that an accuracy between the actual and the generated data was within the range of 75 to 92%. Thus, the CSA approach shows a new method in rainfall data prediction.
    Matched MeSH terms: Forecasting/methods*
  13. Bulgiba AM
    Asia Pac J Public Health, 2004;16(1):64-71.
    PMID: 18839870 DOI: 10.1177/101053950401600111
    In 1998, Malaysia opened its first hospital based on the "paperless and filmless" concept. Two are now in operation, with more to follow. Telemedicine is now being used in some hospitals and is slated to be the technology to watch. Future use of technology in health care will centre on the use of centralised patient databases and more effective use of artificial intelligence. Stumbling blocks include the enormous capital costs involved and difficulty in getting sufficient bandwidth to support applications on a national scale. Problems with the use of information technology in developing countries still remain; mainly inadequate skilled resources to operate and maintain the technology, lack of home-grown technology, insufficient experience in the use of information technology in health care and the attitudes of some health staff. The challenge for those involved in this field will not be in building new "paperless and filmless" institutions but in transforming current "paper and film-based" institutions to "paperless and filmless" ones and changing the mindset of health staff. Universities and medical schools must be prepared to respond to this new wave by incorporating elements of medical/health informatics in their curriculum and assisting governments in the planning and implementation of these projects. The experience of the UMMC is highlighted as an example of the difficulty of transforming a paper-based hospital to a "paperless and filmless" hospital.
    Matched MeSH terms: Forecasting*
  14. Yong NK, Awang N
    Environ Monit Assess, 2019 Jan 11;191(2):64.
    PMID: 30635772 DOI: 10.1007/s10661-019-7209-6
    This study presents the use of a wavelet-based time series model to forecast the daily average particulate matter with an aerodynamic diameter of less than 10 μm (PM10) in Peninsular Malaysia. The highlight of this study is the use of a discrete wavelet transform (DWT) in order to improve the forecast accuracy. The DWT was applied to convert the highly variable PM10 series into more stable approximations and details sub-series, and the ARIMA-GARCH time series models were developed for each sub-series. Two different forecast periods, one was during normal days, while the other was during haze episodes, were designed to justify the usefulness of DWT. The models' performance was evaluated by four indices, namely root mean square error, mean absolute percentage error, probability of detection and false alarm rate. The results showed that the model incorporated with DWT yielded more accurate forecasts than the conventional method without DWT for both the forecast periods, and the improvement was more prominent for the period during the haze episodes.
    Matched MeSH terms: Forecasting/methods*
  15. Vijayasarveswari V, Andrew AM, Jusoh M, Sabapathy T, Raof RAA, Yasin MNM, et al.
    PLoS One, 2020;15(8):e0229367.
    PMID: 32790672 DOI: 10.1371/journal.pone.0229367
    Breast cancer is the most common cancer among women and it is one of the main causes of death for women worldwide. To attain an optimum medical treatment for breast cancer, an early breast cancer detection is crucial. This paper proposes a multi- stage feature selection method that extracts statistically significant features for breast cancer size detection using proposed data normalization techniques. Ultra-wideband (UWB) signals, controlled using microcontroller are transmitted via an antenna from one end of the breast phantom and are received on the other end. These ultra-wideband analogue signals are represented in both time and frequency domain. The preprocessed digital data is passed to the proposed multi- stage feature selection algorithm. This algorithm has four selection stages. It comprises of data normalization methods, feature extraction, data dimensional reduction and feature fusion. The output data is fused together to form the proposed datasets, namely, 8-HybridFeature, 9-HybridFeature and 10-HybridFeature datasets. The classification performance of these datasets is tested using the Support Vector Machine, Probabilistic Neural Network and Naïve Bayes classifiers for breast cancer size classification. The research findings indicate that the 8-HybridFeature dataset performs better in comparison to the other two datasets. For the 8-HybridFeature dataset, the Naïve Bayes classifier (91.98%) outperformed the Support Vector Machine (90.44%) and Probabilistic Neural Network (80.05%) classifiers in terms of classification accuracy. The finalized method is tested and visualized in the MATLAB based 2D and 3D environment.
    Matched MeSH terms: Forecasting/methods*
  16. Norrulashikin MA, Yusof F, Hanafiah NHM, Norrulashikin SM
    PLoS One, 2021;16(7):e0254137.
    PMID: 34288925 DOI: 10.1371/journal.pone.0254137
    The increasing trend in the number new cases of influenza every year as reported by WHO is concerning, especially in Malaysia. To date, there is no local research under healthcare sector that implements the time series forecasting methods to predict future disease outbreak in Malaysia, specifically influenza. Addressing the problem could increase awareness of the disease and could help healthcare workers to be more prepared in preventing the widespread of the disease. This paper intends to perform a hybrid ARIMA-SVR approach in forecasting monthly influenza cases in Malaysia. Autoregressive Integrated Moving Average (ARIMA) model (using Box-Jenkins method) and Support Vector Regression (SVR) model were used to capture the linear and nonlinear components in the monthly influenza cases, respectively. It was forecasted that the performance of the hybrid model would improve. The data from World Health Organization (WHO) websites consisting of weekly Influenza Serology A cases in Malaysia from the year 2006 until 2019 have been used for this study. The data were recategorized into monthly data. The findings of the study showed that the monthly influenza cases could be efficiently forecasted using three comparator models as all models outperformed the benchmark model (Naïve model). However, SVR with linear kernel produced the lowest values of RMSE and MAE for the test dataset suggesting the best performance out of the other comparators. This suggested that SVR has the potential to produce more consistent results in forecasting future values when compared with ARIMA and the ARIMA-SVR hybrid model.
    Matched MeSH terms: Forecasting/methods*
  17. Soyiri IN, Reidpath DD
    Environ Health Prev Med, 2013 Jan;18(1):1-9.
    PMID: 22949173 DOI: 10.1007/s12199-012-0294-6
    Health forecasting is a novel area of forecasting, and a valuable tool for predicting future health events or situations such as demands for health services and healthcare needs. It facilitates preventive medicine and health care intervention strategies, by pre-informing health service providers to take appropriate mitigating actions to minimize risks and manage demand. Health forecasting requires reliable data, information and appropriate analytical tools for the prediction of specific health conditions or situations. There is no single approach to health forecasting, and so various methods have often been adopted to forecast aggregate or specific health conditions. Meanwhile, there are no defined health forecasting horizons (time frames) to match the choices of health forecasting methods/approaches that are often applied. The key principles of health forecasting have not also been adequately described to guide the process. This paper provides a brief introduction and theoretical analysis of health forecasting. It describes the key issues that are important for health forecasting, including: definitions, principles of health forecasting, and the properties of health data, which influence the choices of health forecasting methods. Other matters related to the value of health forecasting, and the general challenges associated with developing and using health forecasting services are discussed. This overview is a stimulus for further discussions on standardizing health forecasting approaches and methods that will facilitate health care and health services delivery.
    Matched MeSH terms: Forecasting*
  18. Al-Jumeily D, Ghazali R, Hussain A
    PLoS One, 2014;9(8):e105766.
    PMID: 25157950 DOI: 10.1371/journal.pone.0105766
    Forecasting naturally occurring phenomena is a common problem in many domains of science, and this has been addressed and investigated by many scientists. The importance of time series prediction stems from the fact that it has wide range of applications, including control systems, engineering processes, environmental systems and economics. From the knowledge of some aspects of the previous behaviour of the system, the aim of the prediction process is to determine or predict its future behaviour. In this paper, we consider a novel application of a higher order polynomial neural network architecture called Dynamic Ridge Polynomial Neural Network that combines the properties of higher order and recurrent neural networks for the prediction of physical time series. In this study, four types of signals have been used, which are; The Lorenz attractor, mean value of the AE index, sunspot number, and heat wave temperature. The simulation results showed good improvements in terms of the signal to noise ratio in comparison to a number of higher order and feedforward neural networks in comparison to the benchmarked techniques.
    Matched MeSH terms: Forecasting
  19. Jalaludin MA, Arokiasamy JT
    Med J Malaysia, 2002 Dec;57 Suppl E:3-4.
    PMID: 12733183
    Matched MeSH terms: Forecasting
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links