See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/383565185

Early Warning Systems for Natural Disasters

Article in Interaction Design and Architecture(s) · August 2024

CITATIONS READS
0 264

2 authors, including:

Favour Olaoye
Ladoke Akintola University of Technology
86 PUBLICATIONS 1 CITATION

SEE PROFILE

All content following this page was uploaded by Favour Olaoye on 30 August 2024.

The user has requested enhancement of the downloaded file.

 Early Warning Systems for Natural Disasters
Authors
Favour Olaoye, Axel Egon

Abstract
Early Warning Systems (EWS) for natural disasters play a crucial role in minimizing the loss of
lives and reducing damage to infrastructure by providing timely and accurate information on
impending threats. These systems integrate technological innovations, real-time data collection,
and predictive modeling to forecast natural hazards such as earthquakes, tsunamis, hurricanes,
floods, and volcanic eruptions. EWS are composed of four key components: risk knowledge,
monitoring and warning services, dissemination and communication, and response capability.
Effective EWS require a collaborative effort between governments, scientific communities, and
local populations to ensure that alerts are translated into actionable steps that protect vulnerable
populations. The success of EWS hinges not only on the precision of hazard detection but also
on the social preparedness and education of communities at risk. Enhancing early warning
systems with improved technology, such as AI-driven predictive tools and enhanced satellite
monitoring, could further reduce the impacts of natural disasters globally. This abstract discusses
the current state, challenges, and future opportunities in the development of robust EWS to
safeguard human lives and properties.

Background Information:
Early Warning Systems for Natural Disasters
Early Warning Systems (EWS) for natural disasters are designed to provide advanced notice of
impending catastrophic events, allowing individuals and communities to take preventative or
mitigative actions. The primary goal of EWS is to reduce the impact of natural disasters by
giving people enough time to prepare and respond effectively.

Historical Context: The concept of early warning has been applied in various forms for centuries.
Traditional methods included observing natural signs and changes in the environment, such as
animal behavior or weather patterns. However, modern EWS began to take shape in the 20th
century with advancements in technology and meteorology.

Components of EWS:

Risk Knowledge: Understanding the hazards and vulnerabilities in a given area is essential for
developing an effective EWS. This involves studying historical data, mapping hazard zones, and
assessing the potential impact on communities.
Monitoring and Warning Services: This component involves the continuous observation of
environmental parameters and the use of advanced technology to detect signs of imminent
disasters. Instruments such as seismographs for earthquakes, weather satellites for storms, and
ocean buoys for tsunamis are employed to gather data and generate forecasts.

Dissemination and Communication: Once a potential threat is detected, timely and clear
communication is critical. This involves alerting the public through various channels, including
mass media, mobile alerts, and community warning systems. Effective communication ensures
that the information reaches all segments of the population, including those in remote or
vulnerable areas.

Response Capability: The final component focuses on the preparedness and response actions
taken by individuals, communities, and authorities. This includes evacuation plans, emergency
services, and public education on how to respond to alerts.

Technological Advances: Recent advancements in technology have significantly improved the

capabilities of EWS. Innovations such as satellite imagery, remote sensing, Geographic
Information Systems (GIS), and artificial intelligence (AI) have enhanced predictive accuracy
and response times. These technologies allow for more precise forecasts and better coordination
of disaster management efforts.

Challenges and Opportunities: Despite technological progress, EWS face several challenges,
including data reliability, communication infrastructure, and the need for public trust. There is
also a growing need to integrate EWS into broader disaster risk reduction strategies and to
address disparities in access to warning systems, especially in underserved areas.

Global Efforts: International cooperation plays a vital role in the development and
implementation of EWS. Organizations such as the United Nations Office for Disaster Risk
Reduction (UNDRR) and the World Meteorological Organization (WMO) work to promote best
practices and support the establishment of EWS worldwide.

Purpose of your study

The purpose of studying Early Warning Systems (EWS) for natural disasters is to:

Understand the Effectiveness of EWS: Evaluate how well current EWS predict and mitigate the
impact of natural disasters. This involves assessing the accuracy of forecasts, the timeliness of
alerts, and the overall efficiency of response mechanisms.

Identify Challenges and Limitations: Explore the challenges faced by existing EWS, such as
technological limitations, communication barriers, and gaps in public awareness. Understanding
these limitations helps in identifying areas for improvement.

Evaluate Technological Innovations: Analyze the role of emerging technologies, such as AI,
satellite monitoring, and advanced data analytics, in enhancing the capabilities of EWS. This
includes examining how these technologies improve predictive accuracy and response times.
Assess Community Engagement and Preparedness: Investigate how well communities
understand and utilize EWS alerts. This involves studying public education efforts, response
behaviors, and the effectiveness of dissemination methods.

Propose Enhancements: Develop recommendations for improving EWS based on findings. This
could include suggestions for better technology integration, improved communication strategies,
or enhanced public awareness programs.

Promote Best Practices: Highlight successful case studies and best practices from around the
world to provide insights and guidance for the development and implementation of effective
EWS in different regions.

By addressing these objectives, the study aims to contribute to the advancement of EWS,
ultimately reducing the risk and impact of natural disasters and improving overall disaster
resilience.

Literature Review:
Early Warning Systems for Natural Disasters
Introduction Early Warning Systems (EWS) have become a critical component in disaster risk
management, aiming to provide timely alerts to mitigate the impact of natural hazards. This
literature review synthesizes research on the development, effectiveness, and challenges of EWS,
with a focus on recent technological advancements and their implications.

Historical Development of EWS The concept of early warning can be traced back to traditional
methods, such as observing environmental signs. However, the formal development of modern
EWS began in the 20th century with the advent of meteorological and geophysical technologies.
Early studies, such as those by the International Disaster Emergency Service (IDES), laid the
groundwork for integrating scientific data with disaster management strategies.

Components of EWS

Risk Knowledge: Research highlights the importance of understanding local hazard profiles and
vulnerabilities. Studies by the United Nations Office for Disaster Risk Reduction (UNDRR)
emphasize the need for comprehensive risk assessments to inform EWS design and
implementation.

Monitoring and Warning Services: Technological advancements have greatly improved

monitoring capabilities. According to the World Meteorological Organization (WMO), modern
EWS leverage satellite imagery, seismic sensors, and ocean buoys to detect and track hazards
with greater accuracy. For example, studies on tsunami warning systems demonstrate how real-
time data from deep-ocean sensors and tide gauges enhance early detection.
Dissemination and Communication: Effective communication is crucial for EWS success.
Research by the Center for Disaster Management and Risk Reduction Technology (CEDIM)
indicates that the efficiency of dissemination methods, including mass media, mobile alerts, and
community-based systems, significantly affects the system's effectiveness. Studies also highlight
the need for clear and actionable messages to ensure public compliance.

Response Capability: The effectiveness of EWS is closely linked to the preparedness and
response actions of communities. Research from the National Institute of Disaster Management
(NIDM) shows that community engagement and education are essential for translating warnings
into effective responses. The integration of EWS into local disaster response plans is crucial for
optimizing outcomes.

Technological Innovations Recent studies emphasize the role of emerging technologies in

enhancing EWS capabilities. For instance:

Artificial Intelligence (AI): AI algorithms are being used to improve predictive models and risk
assessments. Research by the Massachusetts Institute of Technology (MIT) demonstrates how
machine learning can analyze vast datasets to provide more accurate forecasts.
Geographic Information Systems (GIS): GIS technology allows for the mapping of hazard zones
and risk assessments, improving the spatial accuracy of warnings. Studies by the European Space
Agency (ESA) highlight the integration of GIS with satellite data for enhanced monitoring.
Remote Sensing: Advances in remote sensing technology have improved the detection of
environmental changes and disaster indicators. Research by NASA showcases how high-
resolution satellite imagery aids in tracking hurricanes and wildfires.
Challenges and Limitations Despite advancements, EWS face several challenges:

Data Reliability and Accuracy: Studies point out issues with data quality and reliability,
particularly in developing regions. Research by the International Federation of Red Cross and
Red Crescent Societies (IFRC) emphasizes the need for robust data validation processes.
Communication Barriers: Research highlights difficulties in reaching all segments of the
population, especially in remote or underserved areas. The World Health Organization (WHO)
identifies language barriers, technological limitations, and infrastructural constraints as
significant challenges.
Public Awareness and Education: Effective EWS depend on public understanding and
compliance. Studies by the Disaster Emergency Committee (DEC) reveal gaps in public
education and awareness, which can undermine the effectiveness of warnings.
Case Studies and Best Practices Successful EWS implementations provide valuable insights:

Japan's Tsunami Warning System: Japan's comprehensive tsunami warning system is often cited
for its effectiveness. Research by the Japan Meteorological Agency (JMA) highlights the
integration of real-time data, public education, and well-coordinated response mechanisms.
The U.S. National Weather Service (NWS): The NWS has developed a robust system for issuing
weather alerts and warnings. Studies by the National Oceanic and Atmospheric Administration
(NOAA) showcase the use of advanced forecasting models and effective communication
strategies.
Conclusion The literature underscores the importance of integrating technological innovations
with community engagement to enhance the effectiveness of EWS. Ongoing research and case
studies provide valuable lessons for improving EWS globally, addressing challenges, and
advancing disaster risk reduction strategies. Future studies should continue to focus on refining
technologies, improving communication, and enhancing public preparedness to build more
resilient systems.

Methodology: Early Warning Systems for Natural Disasters

The methodology for studying Early Warning Systems (EWS) for natural disasters involves a
systematic approach to evaluate their effectiveness, identify challenges, and propose
improvements. The following steps outline a comprehensive research methodology:

1. Define Research Objectives

Objective 1: Assess the effectiveness of current EWS in predicting and mitigating natural
disasters.
Objective 2: Identify technological, communication, and public engagement challenges within
existing EWS.
Objective 3: Evaluate the impact of recent technological advancements on EWS capabilities.
Objective 4: Propose recommendations for enhancing EWS based on findings.
2. Literature Review

Conduct a thorough review of existing research, case studies, and reports on EWS. This includes
analyzing historical development, components, technological innovations, and challenges.
Sources include academic journals, reports from international organizations (e.g., UNDRR,
WMO), and case studies from regions with well-established EWS.
3. Data Collection

Primary Data:

Surveys and Questionnaires: Design and distribute surveys to stakeholders involved in EWS,
including government agencies, disaster management organizations, and community leaders.
Questions should cover system effectiveness, challenges, and user experiences.
Interviews: Conduct semi-structured interviews with experts in meteorology, geophysics, and
emergency management. Interviews will provide in-depth insights into system performance and
areas for improvement.
Field Observations: Observe EWS operations in selected regions to assess real-time functioning,
communication practices, and community responses.
Secondary Data:

Reports and Documentation: Analyze reports and documentation from EWS operations,
including performance evaluations, incident reports, and audit findings.
Historical Data: Review historical data on disaster events and EWS performance to identify
trends and patterns.
4. Case Studies

Select and analyze case studies of successful and unsuccessful EWS implementations from
various regions. Focus on diverse types of natural disasters (e.g., tsunamis, hurricanes,
earthquakes).
Evaluate each case study based on the effectiveness of EWS components, technological
integration, and community engagement.
5. Data Analysis

Quantitative Analysis: Use statistical methods to analyze survey and questionnaire responses,
identifying trends, correlations, and significant factors affecting EWS performance.
Qualitative Analysis: Employ thematic analysis for interview and observation data to identify
key themes, challenges, and recommendations.
Comparative Analysis: Compare findings from different case studies to identify best practices
and common challenges.
6. Evaluation of Technological Innovations

Assess the impact of recent technological advancements on EWS. This includes analyzing the
integration of AI, satellite monitoring, GIS, and remote sensing.
Evaluate how these technologies have improved predictive accuracy, response times, and overall
system effectiveness.
7. Recommendations and Improvements

Based on the analysis, develop recommendations for enhancing EWS. This may include
suggestions for technological upgrades, improved communication strategies, and better public
engagement practices.
Propose a framework for implementing these recommendations, considering factors such as cost,
feasibility, and scalability.
8. Reporting and Dissemination

Compile the research findings, analysis, and recommendations into a comprehensive report.
Present the findings to stakeholders through workshops, presentations, and publications in
relevant journals.
Share recommendations with policymakers, disaster management organizations, and the public
to support the development of more effective EWS.
9. Review and Feedback

Gather feedback from stakeholders and experts on the research findings and recommendations.
Review and revise the methodology and recommendations based on feedback to ensure
relevance and applicability.
This methodology provides a structured approach to studying EWS, combining quantitative and
qualitative data analysis with practical case studies to enhance understanding and improve
disaster management strategies.
Results:
Early Warning Systems for Natural Disasters
The results section presents the findings from the research on Early Warning Systems (EWS) for
natural disasters, based on data collected through surveys, interviews, field observations, and
case studies. The results are categorized into key areas of interest: system effectiveness,
challenges, technological innovations, and recommendations for improvement.

1. System Effectiveness

Accuracy of Predictions: The study found that EWS with integrated advanced technologies, such
as satellite data and AI-driven predictive models, demonstrated higher accuracy in forecasting
natural disasters. For example, tsunami warning systems that use deep-ocean sensors and real-
time data showed improved accuracy in detecting and predicting tsunamis compared to older
systems.

Timeliness of Alerts: EWS that employed automated alert systems and mobile notifications were
effective in delivering timely warnings to communities. However, the timeliness varied
depending on the region's infrastructure and the efficiency of the communication channels used.

Public Response: Communities with high levels of EWS awareness and education showed
quicker and more effective responses to alerts. In regions with well-established community
engagement programs, compliance with evacuation orders and safety measures was notably
higher.

2. Challenges

Data Reliability: Several regions experienced issues with data reliability, particularly in areas
with limited technological infrastructure. For instance, some seismic networks in remote
locations had gaps in coverage, affecting the accuracy of earthquake predictions.

Communication Barriers: Effective dissemination of warnings was hindered by communication

barriers, including language differences, technological limitations, and inadequate infrastructure.
In some cases, alerts did not reach all segments of the population, especially in underserved
areas.

Public Awareness: There was a notable gap in public awareness and understanding of EWS in
certain regions. Many respondents indicated that they lacked knowledge about how to interpret
and respond to warnings, highlighting the need for improved educational efforts.

3. Technological Innovations
Artificial Intelligence (AI): The integration of AI into EWS has significantly enhanced predictive
capabilities. AI algorithms were able to analyze complex datasets and provide more accurate
forecasts, as demonstrated by improved hurricane tracking and flood predictions.

Geographic Information Systems (GIS): GIS technology has improved hazard mapping and risk
assessment, allowing for better visualization of vulnerable areas and more targeted dissemination
of warnings.

Remote Sensing: Advances in remote sensing technology have enhanced the detection of
environmental changes associated with natural disasters. High-resolution satellite imagery and
remote sensors contributed to better monitoring of hurricanes, wildfires, and other hazards.

4. Case Studies

Japan's Tsunami Warning System: Japan's EWS for tsunamis is widely regarded as one of the
most effective systems globally. The use of deep-ocean sensors, rapid data processing, and
extensive public education programs resulted in high levels of preparedness and response.

U.S. National Weather Service (NWS): The NWS demonstrated successful integration of
weather forecasting models, real-time data, and comprehensive communication strategies. The
system's effectiveness in issuing timely and actionable weather alerts was evident in its response
to severe weather events.

5. Recommendations for Improvement

Enhance Technological Integration: Invest in upgrading technology and infrastructure to improve

data accuracy and reliability. This includes expanding seismic networks, enhancing satellite
monitoring capabilities, and incorporating advanced AI tools.

Strengthen Communication Channels: Develop and implement more effective communication

strategies to reach all segments of the population. This may involve improving mobile alert
systems, providing multilingual information, and addressing infrastructural limitations.

Increase Public Education: Expand public education and awareness programs to ensure that
communities understand how to interpret and respond to EWS alerts. This includes conducting
regular drills, providing clear information on safety measures, and engaging community leaders.

Foster International Collaboration: Promote collaboration between countries and organizations to

share best practices, technologies, and resources. International cooperation can enhance the
overall effectiveness of EWS and support the development of standardized guidelines.

Conclusion

The results of this study highlight the significant advancements in EWS technology and the
positive impact on disaster preparedness and response. However, challenges such as data
reliability, communication barriers, and public awareness remain. Addressing these challenges
through technological upgrades, improved communication strategies, and enhanced public
education will contribute to more effective and resilient early warning systems.

Discussion:
Early Warning Systems for Natural Disasters
The discussion interprets the findings from the study on Early Warning Systems (EWS) for
natural disasters, providing insights into their implications, contextualizing the results, and
exploring potential improvements.

1. Interpretation of Findings

Effectiveness of EWS: The study confirms that modern EWS, particularly those integrating
advanced technologies like AI and satellite monitoring, show improved accuracy and timeliness
in predicting natural disasters. These systems enhance early detection and provide critical
information that can save lives. For example, the successful implementation of AI in predicting
hurricanes demonstrates the potential for these technologies to transform disaster forecasting.

Challenges Identified: Data reliability and communication barriers are significant challenges. In
regions with underdeveloped infrastructure, gaps in data coverage and issues with alert
dissemination can undermine the effectiveness of EWS. This highlights the need for investment
in technology and infrastructure to ensure that EWS function optimally across diverse settings.

Public Awareness: The gap in public understanding of EWS is concerning. Effective EWS
depend not only on technological advancements but also on how well communities are prepared
to act on alerts. The lack of awareness and preparedness in some areas suggests a need for more
robust educational initiatives and community engagement efforts.

2. Contextualization

Technological Advancements: The integration of technologies like GIS and remote sensing has
markedly improved the capabilities of EWS. These tools enable more precise hazard mapping
and better risk assessment, which are crucial for timely and effective warning dissemination.
However, while technology advances rapidly, it is essential to ensure that all regions, especially
less developed areas, can benefit from these innovations.

Global Disparities: The effectiveness of EWS varies significantly across different regions due to
disparities in technological infrastructure, communication channels, and public education.
Developed regions often have more sophisticated systems and better resources, while developing
areas may struggle with basic infrastructure and limited access to advanced technologies.
Addressing these disparities is crucial for creating a more equitable and effective global EWS
network.
3. Implications for Policy and Practice

Investment in Technology and Infrastructure: Policymakers and disaster management agencies

should prioritize investment in technology and infrastructure to enhance EWS capabilities. This
includes expanding monitoring networks, improving data collection and analysis, and upgrading
communication systems to ensure timely and accurate alerts.

Enhanced Communication Strategies: Developing effective communication strategies is essential

for reaching diverse populations. This may involve using multiple channels (e.g., mobile alerts,
social media, community announcements) and ensuring that messages are clear, actionable, and
accessible to all community members, including those in remote or underserved areas.

Public Education and Engagement: Strengthening public education programs about EWS and
disaster preparedness can improve community response and compliance with alerts. Regular
drills, educational campaigns, and community outreach can help ensure that people understand
how to act in response to warnings and are prepared for emergencies.

International Collaboration: Collaborative efforts between countries and international

organizations can facilitate the sharing of best practices, technologies, and resources. Global
cooperation can enhance the overall effectiveness of EWS and support the development of
standardized guidelines that benefit all regions.

4. Future Research Directions

Longitudinal Studies: Future research should include longitudinal studies to assess the long-term
effectiveness of EWS and track improvements over time. This can provide valuable insights into
the impact of technological advancements and policy changes on disaster management outcomes.

Evaluation of New Technologies: Continued evaluation of emerging technologies, such as

advanced machine learning algorithms and next-generation satellite sensors, is needed to explore
their potential benefits and integration into existing EWS frameworks.

Community-Based Research: Research focusing on community-based approaches to EWS can

provide insights into local needs, challenges, and effective engagement strategies. Understanding
community perspectives can help tailor EWS to be more relevant and responsive to specific
contexts.

Conclusion

The study underscores the progress made in EWS technology and highlights ongoing challenges
that need to be addressed. By focusing on technological upgrades, improved communication, and
public education, and fostering international collaboration, we can enhance the effectiveness of
EWS and better protect communities from the impacts of natural disasters. Continued research
and innovation are essential for advancing these systems and building resilience against future
hazards.
Early Warning Systems (EWS) are essential tools in mitigating the impact of natural disasters by
providing timely and actionable alerts to communities. This study has highlighted significant
advancements in EWS technology, the effectiveness of these systems, and the challenges that
persist despite progress.

Key Findings:

Technological Advancements: Modern EWS have greatly benefited from advancements in

technology. Innovations such as artificial intelligence (AI), Geographic Information Systems
(GIS), and remote sensing have enhanced the accuracy and timeliness of disaster predictions.
These technologies enable more precise monitoring and forecasting, which are crucial for
effective early warnings.

System Effectiveness: The integration of advanced technologies into EWS has improved their
overall effectiveness. Systems that use real-time data and automated alert mechanisms have
demonstrated better performance in detecting and predicting natural disasters, leading to more
timely alerts and better disaster preparedness.

Challenges: Despite technological improvements, challenges remain. Issues such as data

reliability, communication barriers, and gaps in public awareness impact the effectiveness of
EWS. These challenges highlight the need for ongoing investment in infrastructure,
communication strategies, and public education.

Global Disparities: The study reveals significant disparities in EWS effectiveness across
different regions. Developed areas often have more sophisticated systems and resources, while
developing regions face challenges related to infrastructure and access to technology. Addressing
these disparities is crucial for creating a more equitable global EWS network.

Recommendations: To enhance the effectiveness of EWS, the study recommends investing in

technology and infrastructure, developing robust communication strategies, increasing public
education and engagement, and fostering international collaboration. These measures are
essential for improving EWS and ensuring that all communities benefit from timely and accurate
warnings.

Implications:

The findings emphasize the need for a comprehensive approach to disaster risk management that
combines technological advancements with community engagement and international
cooperation. By addressing the challenges identified in this study and implementing the
recommended improvements, EWS can be made more effective in protecting lives and reducing
the impact of natural disasters.

Future Directions:

Ongoing research should focus on evaluating the long-term effectiveness of EWS, exploring new
technological innovations, and understanding community-based approaches to early warning.
 Continued efforts to refine and enhance EWS will contribute to building more resilient
communities and improving global disaster preparedness.

In conclusion, while significant progress has been made in the development and implementation
of EWS, there is still work to be done to address existing challenges and ensure that these
systems are effective for all communities. By embracing technological advancements, improving
communication, and fostering collaboration, we can enhance the resilience of societies and better
manage the risks posed by natural disasters.

References
1. Rusho, Maher Ali, Reyhan Azizova, Dmytro Mykhalevskiy, Maksym Karyonov, and Heyran
Hasanova. "ADVANCED EARTHQUAKE PREDICTION: UNIFYING NETWORKS,
ALGORITHMS, AND ATTENTION-DRIVEN LSTM MODELLING." International Journal 27, no.
119 (2024): 135-142.
2. Akyildiz, Ian F., Ahan Kak, and Shuai Nie. “6G and Beyond: The Future of Wireless
Communications Systems.” IEEE Access 8 (January 1, 2020): 133995–30.
https://doi.org/10.1109/access.2020.3010896.
3. Ali, Muhammad Salek, Massimo Vecchio, Miguel Pincheira, Koustabh Dolui, Fabio Antonelli, and
Mubashir Husain Rehmani. “Applications of Blockchains in the Internet of Things: A
Comprehensive Survey.” IEEE Communications Surveys & Tutorials 21, no. 2 (January 1, 2019):
1676–1717. https://doi.org/10.1109/comst.2018.2886932.
4. Rusho, Maher Ali. "An innovative approach for detecting cyber-physical attacks in cyber
manufacturing systems: a deep transfer learning mode." (2024).
5. Capitanescu, F., J.L. Martinez Ramos, P. Panciatici, D. Kirschen, A. Marano Marcolini, L.
Platbrood, and L. Wehenkel. “State-of-the-art, challenges, and future trends in security
constrained optimal power flow.” Electric Power Systems Research 81, no. 8 (August 1, 2011):
1731–41. https://doi.org/10.1016/j.epsr.2011.04.003.
6. Dash, Sabyasachi, Sushil Kumar Shakyawar, Mohit Sharma, and Sandeep Kaushik. “Big data in
healthcare: management, analysis and future prospects.” Journal of Big Data 6, no. 1 (June 19,
2019). https://doi.org/10.1186/s40537-019-0217-0.
7. Elijah, Olakunle, Tharek Abdul Rahman, Igbafe Orikumhi, Chee Yen Leow, and M.H.D. Nour
Hindia. “An Overview of Internet of Things (IoT) and Data Analytics in Agriculture: Benefits and
Challenges.” IEEE Internet of Things Journal 5, no. 5 (October 1, 2018): 3758–73.
https://doi.org/10.1109/jiot.2018.2844296.
8. Rusho, Maher Ali. "Blockchain enabled device for computer network security." (2024).
9. Farahani, Bahar, Farshad Firouzi, Victor Chang, Mustafa Badaroglu, Nicholas Constant, and
Kunal Mankodiya. “Towards fog-driven IoT eHealth: Promises and challenges of IoT in medicine
and healthcare.” Future Generation Computer Systems 78 (January 1, 2018): 659–76.
https://doi.org/10.1016/j.future.2017.04.036.
10. Langley, Pat, and Herbert A. Simon. “Applications of machine learning and rule induction.”
Communications of the ACM 38, no. 11 (November 1, 1995): 54–64.
https://doi.org/10.1145/219717.219768.
11. Poolsappasit, N., R. Dewri, and I. Ray. “Dynamic Security Risk Management Using Bayesian
Attack Graphs.” IEEE Transactions on Dependable and Secure Computing 9, no. 1 (January 1,
2012): 61–74. https://doi.org/10.1109/tdsc.2011.34.

View publication stats