Data Science and Analytics: An Overview from Data-Driven Smart Computing, Decision-Making and Applications Perspective

Towards equitable AI in oncology

Artificial intelligence (AI) stands at the threshold of revolutionizing clinical oncology, with considerable potential to improve early cancer detection and risk assessment, and to enable more accurate personalized treatment recommendations. However, a notable imbalance exists in the distribution of the benefits of AI, which disproportionately favour those living in specific geographical locations and in specific populations. In this Perspective, we discuss the need to foster the development of equitable AI tools that are both accurate in and accessible to a diverse range of patient populations, including those in low-income to middle-income countries. We also discuss some of the challenges and potential solutions in attaining equitable AI, including addressing the historically limited representation of diverse populations in existing clinical datasets and the use of inadequate clinical validation methods. Additionally, we focus on extant sources of inequity including the type of model approach (such as deep learning, and feature engineering-based methods), the implications of dataset curation strategies, the need for rigorous validation across a variety of populations and settings, and the risk of introducing contextual bias that comes with developing tools predominantly in high-income countries.

Autonomous Image-Based Corrosion Detection in Steel Structures Using Deep Learning

Steel structures are susceptible to corrosion due to their exposure to the environment. Currently used non-destructive techniques require inspector involvement. Inaccessibility of the defective part may lead to unnoticed corrosion, allowing the corrosion to propagate and cause catastrophic structural failure over time. Autonomous corrosion detection is essential for mitigating these problems. This study investigated the effect of the type of encoder-decoder neural network and the training strategy that works the best to automate the segmentation of corroded pixels in visual images. Models using pre-trained DesnseNet121 and EfficientNetB7 backbones yielded 96.78% and 98.5% average pixel-level accuracy, respectively. Deeper EffiecientNetB7 performed the worst, with only 33% true-positive values, which was 58% less than ResNet34 and the original UNet. ResNet 34 successfully classified the corroded pixels, with 2.98% false positives, whereas the original UNet predicted 8.24% of the non-corroded pixels as corroded when tested on a specific set of images exclusive to the investigated training dataset. Deep networks were found to be better for transfer learning than full training, and a smaller dataset could be one of the reasons for performance degradation. Both fully trained conventional UNet and ResNet34 models were tested on some external images of different steel structures with different colors and types of corrosion, with the ResNet 34 backbone outperforming conventional UNet.

Data-driven evolution of water quality models: An in-depth investigation of innovative outlier detection approaches-A case study of Irish Water Quality Index (IEWQI) model

Recently, there has been a significant advancement in the water quality index (WQI) models utilizing data-driven approaches, especially those integrating machine learning and artificial intelligence (ML/AI) technology. Although, several recent studies have revealed that the data-driven model has produced inconsistent results due to the data outliers, which significantly impact model reliability and accuracy. The present study was carried out to assess the impact of data outliers on a recently developed Irish Water Quality Index (IEWQI) model, which relies on data-driven techniques. To the author's best knowledge, there has been no systematic framework for evaluating the influence of data outliers on such models. For the purposes of assessing the outlier impact of the data outliers on the water quality (WQ) model, this was the first initiative in research to introduce a comprehensive approach that combines machine learning with advanced statistical techniques. The proposed framework was implemented in Cork Harbour, Ireland, to evaluate the IEWQI model's sensitivity to outliers in input indicators to assess the water quality. In order to detect the data outlier, the study utilized two widely used ML techniques, including Isolation Forest (IF) and Kernel Density Estimation (KDE) within the dataset, for predicting WQ with and without these outliers. For validating the ML results, the study used five commonly used statistical measures. The performance metric (R2) indicates that the model performance improved slightly (R2 increased from 0.92 to 0.95) in predicting WQ after removing the data outlier from the input. But the IEWQI scores revealed that there were no statistically significant differences among the actual values, predictions with outliers, and predictions without outliers, with a 95 % confidence interval at p < 0.05. The results of model uncertainty also revealed that the model contributed <1 % uncertainty to the final assessment results for using both datasets (with and without outliers). In addition, all statistical measures indicated that the ML techniques provided reliable results that can be utilized for detecting outliers and their impacts on the IEWQI model. The findings of the research reveal that although the data outliers had no significant impact on the IEWQI model architecture, they had moderate impacts on the rating schemes' of the model. This finding indicated that detecting the data outliers could improve the accuracy of the IEWQI model in rating WQ as well as be helpful in mitigating the model eclipsing problem. In addition, the results of the research provide evidence of how the data outliers influenced the data-driven model in predicting WQ and reliability, particularly since the study confirmed that the IEWQI model's could be effective for accurately rating WQ despite the presence of the data outliers in the input. It could occur due to the spatio-temporal variability inherent in WQ indicators. However, the research assesses the influence of data input outliers on the IEWQI model and underscores important areas for future investigation. These areas include expanding temporal analysis using multi-year data, examining spatial outlier patterns, and evaluating detection methods. Moreover, it is essential to explore the real-world impacts of revised rating categories, involve stakeholders in outlier management, and fine-tune model parameters. Analysing model performance across varying temporal and spatial resolutions and incorporating additional environmental data can significantly enhance the accuracy of WQ assessment. Consequently, this study offers valuable insights to strengthen the IEWQI model's robustness and provides avenues for enhancing its utility in broader WQ assessment applications. Moreover, the study successfully adopted the framework for evaluating how data input outliers affect the data-driven model, such as the IEWQI model. The current study has been carried out in Cork Harbour for only a single year of WQ data. The framework should be tested across various domains for evaluating the response of the IEWQI model's in terms of the spatio-temporal resolution of the domain. Nevertheless, the study recommended that future research should be conducted to adjust or revise the IEWQI model's rating schemes and investigate the practical effects of data outliers on updated rating categories. However, the study provides potential recommendations for enhancing the IEWQI model's adaptability and reveals its effectiveness in expanding its applicability in more general WQ assessment scenarios.

Inverting social innovation to transform health system responses to climate change adaptation and mitigation in the global south

Systems thinking is aimed at understanding and solving complex problems that cut across sectors, an approach that requires accurate, timely, and multisectoral data. Citizen-driven big data can advance systems thinking, considering the widespread use of digital devices. Using digital platforms, data from these devices can transform health systems to predict and prevent global health crises and respond rapidly to emerging crises by providing citizens with real-time support. For example, citizens can obtain real-time support to help with public health risks via a digital app, which can predict evolving risks. These big data can be aggregated and visualized on digital dashboards, which can provide decision-makers with advanced data analytics to facilitate jurisdiction-level rapid responses to evolving climate change impacts (e.g., direct public health crisis communication). In the context of climate change, digital platforms can strengthen rapid responses by integrating information across systems (e.g., food, health, and social services) via citizen big data. More importantly, these big data can be used for rapid decision-making,a paradigm-changing approach that can invert social innovation, which we define as co-conceptualizing societal solutions with vulnerable communities to improve economic development with a focus on community wellbeing. However, to foster equitable and inclusive digital partnerships that invert social innovation, it is critical to avoid top-down approaches that sometimes result when researchers in the Global North and South collaborate. Equitable Global South-North partnerships can be built by combining digital citizen science and community-based participatory research to ethically leverage citizen-driven big data for rapid responses across international jurisdictions.

Prediction of potentially toxic elements in water resources using MLP-NN, RBF-NN, and ANFIS: a comprehensive review

Water resources are constantly threatened by pollution of potentially toxic elements (PTEs). In efforts to monitor and mitigate PTEs pollution in water resources, machine learning (ML) algorithms have been utilized to predict them. However, review studies have not paid attention to the suitability of input variables utilized for PTE prediction. Therefore, the present review analyzed studies that employed three ML algorithms: MLP-NN (multilayer perceptron neural network), RBF-NN (radial basis function neural network), and ANFIS (adaptive neuro-fuzzy inference system) to predict PTEs in water. A total of 139 models were analyzed to ascertain the input variables utilized, the suitability of the input variables, the trends of the ML model applications, and the comparison of their performances. The present study identified seven groups of input variables commonly used to predict PTEs in water. Group 1 comprised of physical parameters (P), chemical parameters (C), and metals (M). Group 2 contains only P and C; Group 3 contains only P and M; Group 4 contains only C and M; Group 5 contains only P; Group 6 contains only C; and Group 7 contains only M. Studies that employed the three algorithms proved that Groups 1, 2, 3, 5, and 7 parameters are suitable input variables for forecasting PTEs in water. The parameters of Groups 4 and 6 also proved to be suitable for the MLP-NN algorithm. However, their suitability with respect to the RBF-NN and ANFIS algorithms could not be ascertained. The most commonly predicted PTEs using the MLP-NN algorithm were Fe, Zn, and As. For the RBF-NN algorithm, they were NO3, Zn, and Pb, and for the ANFIS, they were NO3, Fe, and Mn. Based on correlation and determination coefficients (R, R2), the overall order of performance of the three ML algorithms was ANFIS > RBF-NN > MLP-NN, even though MLP-NN was the most commonly used algorithm.

Identifying Risk Indicators of Cardiovascular Disease in Fasa Cohort Study (FACS): An Application of Generalized Linear Mixed-Model Tree

BACKGROUND

Today, cardiovascular disease (CVD) is the most important cause of death around the world. In this study, our main aim was to predict CVD using some of the most important indicators of this disease and present a tree-based statistical framework for detecting CVD patients according to these indicators.

METHODS

We used data from the baseline phase of the Fasa Cohort Study (FACS). The outcome variable was the presence of CVD. The ordinary Tree and generalized linear mixed models (GLMM) were fitted to the data and their predictive power for detecting CVD was compared with the obtained results from the GLMM tree. Statistical analysis was performed using the RStudio software.

RESULTS

Data of 9499 participants aged 35‒70 years were analyzed. The results of the multivariable mixed-effects logistic regression model revealed that participants' age, total cholesterol, marital status, smoking status, glucose, history of cardiac disease or myocardial infarction (MI) in first- and second-degree relatives, and presence of other diseases (like hypertension, depression, chronic headaches, and thyroid disease) were significantly related to the presence of CVD (P<0.05). Fitting the ordinary tree, GLMM, and GLMM tree resulted in area under the curve (AUC) values of 0.58 (0.56, 0.61), 0.81 (0.77, 0.84), and 0.80 (0.76, 0.83), respectively, among the study population. In addition, the tree model had the best specificity at 81% but the lowest sensitivity at 65% compared to the other models.

CONCLUSION

Given the superior performance of the GLMM tree compared with the standard tree and the lack of significant difference with the GLMM, using this model is suggested due to its simpler interpretation and fewer assumptions. Using updated statistical models for more accurate CVD prediction can result in more precise frameworks to aid in proactive patient detection planning.

Regression-Based Machine Learning for Predicting Lifting Movement Pattern Change in People with Low Back Pain

Machine learning (ML) algorithms are crucial within the realm of healthcare applications. However, a comprehensive assessment of the effectiveness of regression algorithms in predicting alterations in lifting movement patterns has not been conducted. This research represents a pilot investigation using regression-based machine learning techniques to forecast alterations in trunk, hip, and knee movements subsequent to a 12-week strength training for people who have low back pain (LBP). The system uses a feature extraction algorithm to calculate the range of motion in the sagittal plane for the knee, trunk, and hip and 12 different regression machine learning algorithms. The results show that Ensemble Tree with LSBoost demonstrated the utmost accuracy in prognosticating trunk movement. Meanwhile, the Ensemble Tree approach, specifically LSBoost, exhibited the highest predictive precision for hip movement. The Gaussian regression with the kernel chosen as exponential returned the highest prediction accuracy for knee movement. These regression models hold the potential to significantly enhance the precision of visualisation of the treatment output for individuals afflicted with LBP.

Machine learning models in clinical practice for the prediction of postoperative complications after major abdominal surgery

Complications after surgery have a major impact on short- and long-term outcomes, and decades of technological advancement have not yet led to the eradication of their risk. The accurate prediction of complications, recently enhanced by the development of machine learning algorithms, has the potential to completely reshape surgical patient management. In this paper, we reflect on multiple issues facing the implementation of machine learning, from the development to the actual implementation of machine learning models in daily clinical practice, providing suggestions on the use of machine learning models for predicting postoperative complications after major abdominal surgery.

Traditional surveys versus ecological momentary assessments: Digital citizen science approaches to improve ethical physical activity surveillance among youth

The role of physical activity (PA) in minimizing non-communicable diseases is well established. Measurement bias can be reduced via ecological momentary assessments (EMAs) deployed via citizen-owned smartphones. This study aims to engage citizen scientists to understand how PA reported digitally by retrospective and prospective measures varies within the same cohort. This study used the digital citizen science approach to collaborate with citizen scientists, aged 13-21 years over eight consecutive days via a custom-built app. Citizen scientists were recruited through schools in Regina, Saskatchewan, Canada in 2018 (August 31-December 31). Retrospective PA was assessed through a survey, which was adapted from three validated PA surveys to suit smartphone-based data collection, and prospective PA was assessed through time-triggered EMAs deployed consecutively every day, from day 1 to day 8, including weekdays and weekends. Data analyses included paired t-tests to understand the difference in PA reported retrospectively and prospectively, and linear regressions to assess contextual and demographic factors associated with PA reported retrospectively and prospectively. Findings showed a significant difference between PA reported retrospectively and prospectively (p = 0.001). Ethnicity (visible minorities: β = - 0.911, 95% C.I. = -1.677, -0.146), parental education (university: β = 0.978, 95% C.I. = 0.308, 1.649), and strength training (at least one day: β = 0.932, 95% C.I. = 0.108, 1.755) were associated with PA reported prospectively. In contrast, the number of active friends (at least one friend: β = 0.741, 95% C.I. = 0.026, 1.458) was associated with retrospective PA. Physical inactivity is the fourth leading cause of mortality globally, which requires accurate monitoring to inform population health interventions. In this digital age, where ubiquitous devices provide real-time engagement capabilities, digital citizen science can transform how we measure behaviours using citizen-owned ubiquitous digital tools to support prevention and treatment of non-communicable diseases.

Machine Learning Techniques Applied to the Study of Drug Transporters

With the advancement of computer technology, machine learning-based artificial intelligence technology has been increasingly integrated and applied in the fields of medicine, biology, and pharmacy, thereby facilitating their development. Transporters have important roles in influencing drug resistance, drug-drug interactions, and tissue-specific drug targeting. The investigation of drug transporter substrates and inhibitors is a crucial aspect of pharmaceutical development. However, long duration and high expenses pose significant challenges in the investigation of drug transporters. In this review, we discuss the present situation and challenges encountered in applying machine learning techniques to investigate drug transporters. The transporters involved include ABC transporters (P-gp, BCRP, MRPs, and BSEP) and SLC transporters (OAT, OATP, OCT, MATE1,2-K, and NET). The aim is to offer a point of reference for and assistance with the progression of drug transporter research, as well as the advancement of more efficient computer technology. Machine learning methods are valuable and attractive for helping with the study of drug transporter substrates and inhibitors, but continuous efforts are still needed to develop more accurate and reliable predictive models and to apply them in the screening process of drug development to improve efficiency and success rates.

What issues are data scientists talking about? Identification of current data science issues using semantic content analysis of Q&A communities

Background

Because of the growing involvement of communities from various disciplines, data science is constantly evolving and gaining popularity. The growing interest in data science-based services and applications presents numerous challenges for their development. Therefore, data scientists frequently turn to various forums, particularly domain-specific Q&A websites, to solve difficulties. These websites evolve into data science knowledge repositories over time. Analysis of such repositories can provide valuable insights into the applications, topics, trends, and challenges of data science.

Methods

In this article, we investigated what data scientists are asking by analyzing all posts to date on DSSE, a data science-focused Q&A website. To discover main topics embedded in data science discussions, we used latent Dirichlet allocation (LDA), a probabilistic approach for topic modeling.

Results

As a result of this analysis, 18 main topics were identified that demonstrate the current interests and issues in data science. We then examined the topics' popularity and difficulty. In addition, we identified the most commonly used tasks, techniques, and tools in data science. As a result, "Model Training", "Machine Learning", and "Neural Networks" emerged as the most prominent topics. Also, "Data Manipulation", "Coding Errors", and "Tools" were identified as the most viewed (most popular) topics. On the other hand, the most difficult topics were identified as "Time Series", "Computer Vision", and "Recommendation Systems". Our findings have significant implications for many data science stakeholders who are striving to advance data-driven architectures, concepts, tools, and techniques.

Advances in Integration, Wearable Applications, and Artificial Intelligence of Biomedical Microfluidics Systems

Microfluidics attracts much attention due to its multiple advantages such as high throughput, rapid analysis, low sample volume, and high sensitivity. Microfluidics has profoundly influenced many fields including chemistry, biology, medicine, information technology, and other disciplines. However, some stumbling stones (miniaturization, integration, and intelligence) strain the development of industrialization and commercialization of microchips. The miniaturization of microfluidics means fewer samples and reagents, shorter times to results, and less footprint space consumption, enabling a high throughput and parallelism of sample analysis. Additionally, micro-size channels tend to produce laminar flow, which probably permits some creative applications that are not accessible to traditional fluid-processing platforms. The reasonable integration of biomedical/physical biosensors, semiconductor microelectronics, communications, and other cutting-edge technologies should greatly expand the applications of current microfluidic devices and help develop the next generation of lab-on-a-chip (LOC). At the same time, the evolution of artificial intelligence also gives another strong impetus to the rapid development of microfluidics. Biomedical applications based on microfluidics normally bring a large amount of complex data, so it is a big challenge for researchers and technicians to analyze those huge and complicated data accurately and quickly. To address this problem, machine learning is viewed as an indispensable and powerful tool in processing the data collected from micro-devices. In this review, we mainly focus on discussing the integration, miniaturization, portability, and intelligence of microfluidics technology.

A Case Study of Enhancing the Data Science Capacity of an RCMI Program at a Historically Black Medical College

As data grows exponentially across diverse fields, the ability to effectively leverage big data has become increasingly crucial. In the field of data science, however, minority groups, including African Americans, are significantly underrepresented. With the strategic role of minority-serving institutions to enhance diversity in the data science workforce and apply data science to health disparities, the National Institute for Minority Health Disparities (NIMHD) provided funding in September 2021 to six Research Centers in Minority Institutions (RCMI) to improve their data science capacity and foster collaborations with data scientists. Meharry Medical College (MMC), a historically Black College/University (HBCU), was among the six awardees. This paper summarizes the NIMHD-funded efforts at MMC, which include offering mini-grants to collaborative research groups, surveys to understand the needs of the community to guide project implementation, and data science training to enhance the data analytics skills of the RCMI investigators, staff, medical residents, and graduate students. This study is innovative as it addressed the urgent need to enhance the data science capacity of the RCMI program at MMC, build a diverse data science workforce, and develop collaborations between the RCMI and MMC's newly established School of Applied Computational Science. This paper presents the progress of this NIMHD-funded project, which clearly shows its positive impact on the local community.

Systematic review of content analysis algorithms based on deep neural networks

Today according to social media, the internet, Etc. Data is rapidly produced and occupies a large space in systems that have resulted in enormous data warehouses; the progress in information technology has significantly increased the speed and ease of data flow.text mining is one of the most important methods for extracting a useful model through extracting and adapting knowledge from data sets. However, many studies have been conducted based on the usage of deep learning for text processing and text mining issues.The idea and method of text mining are one of the fields that seek to extract useful information from unstructured textual data that is used very today. Deep learning and machine learning techniques in classification and text mining and their type are discussed in this paper as well. Neural networks of various kinds, namely, ANN, RNN, CNN, and LSTM, are the subject of study to select the best technique. In this study, we conducted a Systematic Literature Review to extract and associate the algorithms and features that have been used in this area. Based on our search criteria, we retrieved 130 relevant studies from electronic databases between 1997 and 2021; we have selected 43 studies for further analysis using inclusion and exclusion criteria in Section 3.2. According to this study, hybrid LSTM is the most widely used deep learning algorithm in these studies, and SVM in machine learning method high accuracy in result shown.

An Improved K-means Clustering Algorithm Towards an Efficient Data-Driven Modeling

K-means algorithm is one of the well-known unsupervised machine learning algorithms. The algorithm typically finds out distinct non-overlapping clusters in which each point is assigned to a group. The minimum squared distance technique distributes each point to the nearest clusters or subgroups. One of the K-means algorithm’s main concerns is to find out the initial optimal centroids of clusters. It is the most challenging task to determine the optimum position of the initial clusters’ centroids at the very first iteration. This paper proposes an approach to find the optimal initial centroids efficiently to reduce the number of iterations and execution time. To analyze the effectiveness of our proposed method, we have utilized different real-world datasets to conduct experiments. We have first analyzed COVID-19 and patient datasets to show our proposed method’s efficiency. A synthetic dataset of 10M instances with 8 dimensions is also used to estimate the performance of the proposed algorithm. Experimental results show that our proposed method outperforms traditional kmeans++ and random centroids initialization methods regarding the computation time and the number of iterations.

Setting Requirements for a Dashboard to Inform Portuguese Decision-Makers About Environment Health in an Urban Setting

Dashboards are being increasingly used in the health field, and literature points out that accurate and efficient dashboards require not only dealing with data issues, but also ensuring that dashboards are user-friendly and that incorporate users' views and needs. The integration of evidence and data into decision aiding tools, such as dashboards, to assess and monitor environmental health (EH) in urban settings requires careful design. Departing from EH evidence and making use of the views of EH stakeholders and experts, this study aimed at defining requirements for a dashboard to help decision-makers analyzing and visualizing EH information in the Lisbon urban context. In order to set those requirements, it was combined a user-centered with a design card approach to engage EH potential end-users so as to collect their visualization preferences and gather information related to dashboard requirements. Specifically, three online group semi-structured interviews, involving 11 potential end-users from different organizations, were conducted; design cards with a set of visualization options regarding 17 indicators of built and natural environment determinants were used in the interviews to capture participants' preferences and their rationale; questions about other dashboard features were also asked; and the results from the interviews were synthesized into four separate, but interrelated features, and operationalized into 11 requirements for a dashboard to monitor EH in Lisbon. This study contributes to EH literature by producing knowledge to inform dashboard construction, by highlighting issues related with the usability, analysis, and visualization of data to inform EH decision-making in urban contexts, and by designing an approach that can be replicated to other EH dashboard contexts.

COVID-19 analytics: Towards the effect of vaccine brands through analyzing public sentiment of tweets

The COVID-19 outbreak has created effects on everyday life worldwide. Many research teams at major pharmaceutical companies and research institutes in various countries have been producing vaccines since the beginning of the outbreak. There is an impact of gender on vaccine responses, acceptance, and outcomes. Worldwide promotion of the COVID-19 vaccine additionally generates a huge amount of discussions on social media platforms about diverse factors of vaccines including protection and efficacy. Twitter is considered one of the most well-known social media platforms which have been widely used to share a public opinion on vaccine-related problems in the COVID-19 pandemic. However, there is a lack of research work to analyze the public perception of COVID-19 vaccines systematically from a gender perspective. In this paper, we perform an in-depth analysis of the coronavirus vaccine-related tweets to understand the people's sentiment towards various vaccine brands corresponding to the gender level. The proposed method focuses on the effect of COVID-19 vaccines on gender by taking into account descriptive, diagnostic, predictive, and prescriptive analytics on the Twitter dataset. We also conduct experiments with deep learning models to determine the sentiment polarities of tweets, which are positive, neutral, and negative. The results reveal that LSTM performs better compared to other models with an accuracy rate of 85.7%.

Mobile Expert System: Exploring Context-Aware Machine Learning Rules for Personalized Decision-Making in Mobile Applications

Expert systems, a form of artificial intelligence (AI), are typically designed to solve many real-world problems by reasoning through knowledge, which is primarily represented as IF–THEN rules, with the information acquired from humans or domain experts. However, to assume such rules for personalized decision-making in an intelligent, context-aware mobile application is a challenging issue. The reason is that different mobile users may behave differently in various day-to-day situations, i.e., not identical, and thus the rules for personalized services must be reflected according to their symmetrical or asymmetrical behavioral activities. Therefore, our key focus is to solve this issue through adding personalized decision-making intelligence to develop powerful mobile applications to assist the end-users. To achieve our goal, in this paper, we explore on “Mobile Expert System”, where we take into account machine-learning rules as knowledge-base rather than traditional handcrafted static rules. Thus, the concept of a mobile expert system enables the computing and decision-making processes more actionable and intelligent than traditional ones in the domain of mobile analytics and applications. Our experiment section shows that the context-aware machine learning rules discovered from users’ mobile phone data can contribute in building a mobile expert system to solve a particular problem, through making personalized decisions in various context-aware test cases.

Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions

Deep learning (DL), a branch of machine learning (ML) and artificial intelligence (AI) is nowadays considered as a core technology of today’s Fourth Industrial Revolution (4IR or Industry 4.0). Due to its learning capabilities from data, DL technology originated from artificial neural network (ANN), has become a hot topic in the context of computing, and is widely applied in various application areas like healthcare, visual recognition, text analytics, cybersecurity, and many more. However, building an appropriate DL model is a challenging task, due to the dynamic nature and variations in real-world problems and data. Moreover, the lack of core understanding turns DL methods into black-box machines that hamper development at the standard level. This article presents a structured and comprehensive view on DL techniques including a taxonomy considering various types of real-world tasks like supervised or unsupervised. In our taxonomy, we take into account deep networks for supervised or discriminative learning, unsupervised or generative learning as well as hybrid learning and relevant others. We also summarize real-world application areas where deep learning techniques can be used. Finally, we point out ten potential aspects for future generation DL modeling with research directions. Overall, this article aims to draw a big picture on DL modeling that can be used as a reference guide for both academia and industry professionals.