Introduction

Field of Study

Cybersecurity, with an emphasis on app-level protections.

Research Object

The primary focus of this research is on evaluating and contrasting two primary methods for ensuring application security: static analysis and dynamic analysis.

Unit of Analysis

Software applications from a wide range of fields and sectors serve as the core unit of analysis in this study. In order to gauge the efficacy of security measures, these apps are used as test cases. Recent years have seen a rise in security concerns about widely used software programs [5]. The vulnerabilities in these apps have been made clear by a number of cyberattacks and data leaks. Literature analysis suggests that evaluating and contrasting static and dynamic analytic techniques in the context of application security is an important and developing field of research.

The Project's Justification

This study's potential importance rests in the knowledge gaps it may help fill about the relative efficacy of static versus dynamic analytical techniques. Even though application security is a major issue, existing literature seldom provides a thorough examination of the many approaches used to address it [2]. This study intends to add richness to our knowledge of application security by contrasting the benefits and drawbacks of static versus dynamic techniques in the context of real-world vulnerabilities.

Because of the rising necessity of application security in today's increasingly digital environment, this project is of great importance. Safeguarding sensitive data and defending against cyber-attacks is of utmost importance as organizations and individuals increasingly rely on software programs for day-to-day operations. Attackers aim for application flaws because they can result in sensitive information leaks, monetary losses, and brand disrepute. To successfully reduce these dangers, you must be aware of the advantages and disadvantages of various security precautions.

Aims and Objectives:

The fundamental objective of this study is to contrast and contrast the static and dynamic security approaches taken by developers [3]. Among the more specific goals are:

• Code review, abstract syntax tree analysis, and data flow analysis are all examples of static analysis techniques that will be evaluated and ranked on how well they perform in finding security flaws.
• Assessing Dynamic Analysis Methods: Analysing the efficacy of techniques like runtime testing, penetration testing, and fuzz testing in finding security flaws.
• Finding the Best Cases The goal is to find use cases where static and dynamic analysis approaches could work together to give the strongest possible application security.
• To provide developers and organizations with actionable advice for improving the security of their software applications in light of the research findings.

Given the complexity and fluidity of the topic, this research project is an excellent candidate for an IRP [1]. It has the ability to advance our understanding by shedding light on how to optimally combine static and dynamic analysis techniques to improve application security. The results of this study may further advance the subject of Cybersecurity by providing developers, organizations, and security experts with useful information for making well-informed judgements about their own security measures.

Rationale and Hypothesis for the Study

Research question: "What are the relative advantages and disadvantages of static and dynamic security techniques in application development?" is informed by a review of previous studies that show the necessity for a full examination of these techniques. The value of this study in resolving controversies and providing evidence-based insights into the area is highlighted by ongoing discussions over the viability of various approaches.

For this reason, the question "What are the relative advantages and disadvantages of static and dynamic security techniques in application development?" serves as the study's overarching research issue [4]. The lack of information on the relative efficacy of these two strategies drives this investigation. We hope that by investigating this subject, we may help guide judgments about which security techniques to use and how to put them into practice within the realm of application security. In the end, the results of this study can improve software application security, which is good news for both individuals and businesses.

Literature Review

Introduction

The relevance of application-level security in the realm of cybersecurity cannot be overstated in the modern online environment [14]. The necessity for stringent security measures has never been higher than it is now, as software applications become ever more vital to our everyday lives and crucial corporate activities. In this light, the purpose of the literature review is to present a panoramic picture of the dynamic field of application security, with a particular emphasis on the assessment of static and dynamic analytic techniques. Our research project aims to provide new insights into the field of application security, and this study is designed to critically examine current research, identify gaps in knowledge, and lay the groundwork for that.

Application Security Through Static Analysis

When evaluating the safety of software, static analysis methods are invaluable. These techniques allow for a thorough evaluation of source code without ever running it, making it possible to spot potential security problems. Code review is a common kind of static analysis that requires knowledgeable programmers to manually inspect the code for any issues. Reviewing code manually may be helpful for finding security flaws, but it can be time-consuming, resource-intensive, and prone to mistakes due to human error.

Abstract Syntax Tree (AST) analysis is a method for automating static analysis [12]. By generating a tree-like representation of the syntactical structure of a piece of code, AST analysis makes it easier to spot security flaws and sloppy programming techniques. Another static approach, data flow analysis tracks how information is used inside a program to spot problems with input validation and data leakage.

Static analysis has benefits, but it also has certain drawbacks. There is a risk of false positives and overlooked vulnerabilities due to the large amount of code that must be analyzed. In addition, the complexity of current software systems might make it difficult for static analysis to find flaws in large codebases.

Application Security Through Dynamic Analysis

In contrast, dynamic analysis is performed while the program is really running and its behavior is continuously monitored. To find security flaws that aren't obvious from static analysis alone, this method mimics real-world circumstances and input data [11]. Runtime testing, penetration testing, and fuzz testing are all examples of dynamic analysis techniques.

Application responses to different inputs and conditions are evaluated during runtime testing [26]. It can find flaws that are only exploitable while the program is being run. Active efforts are made to compromise the security of the application during penetration testing, which is often performed by ethical hackers. This technique realistically assesses the security of an application by simulating the behaviors of possible attackers [13]. In order to find input validation and error-handling vulnerabilities, fuzz testing deliberately stresses an application by supplying it with random or distorted data.

It might be difficult to spot vulnerabilities using static analysis alone, but dynamic analysis techniques are quite successful at doing just that. However, they are not without their difficulties, such as the difficulty of analyzing dynamic behavior and the need of specialized tools and knowledge to prevent disruptions to routine operations.

Examples from the Real World

Two high-profile case studies—the Heartbleed vulnerability and the Equifax breach—are analyzed to demonstrate the importance of application security measures in the real world.

1. Heartbleed Vulnerability: Dynamic Analysis Shows Promising Results

Secret keys, passwords, and session cookies were all vulnerable to hackers thanks to the Heartbleed flaw in the OpenSSL library in 2014 [15]. Static analysis alone was unable to find this vulnerability due to the complexity of the codebase and a lack of available resources. Dynamic analytic methods were important in discovering the Heartbleed vulnerability. Researchers used attack simulation tools, watched for aberrant OpenSSL library behavior, and eventually found the flaw.

The Heartbleed exploit demonstrates the need for a holistic vulnerability evaluation that incorporates both static and dynamic analysis. Dynamic analysis offered real-world context and confirmation of the vulnerability's existence, although static analysis may have found the code fault theoretically.

• The Equifax Breach was exacerbated by sloppy static analysis and patch management.

The Equifax hack of 2017 was one of the worst data breaches ever. The hack exposed the personal information of 147 million individuals because of a known vulnerability in a web application [8]. The problem may have been found sooner if static analysis had been used in this circumstance. The Equifax application was susceptible to attack because of a flaw in the Apache Struts framework. A code review should have uncovered this vulnerability, however subpar static analysis practices and patch management prevented it from happening.

The Equifax breach highlights the importance of applying patches as soon as they become available once vulnerabilities are detected [24]. Only when vulnerabilities are swiftly addressed via patch management can static analysis provide any real value. There may be legal ramifications, reputational harm, and financial losses if these essential actions are ignored.

Conclusion

By highlighting the significance of both static and dynamic analysis techniques, the literature review concludes by providing a holistic overview of the topic of application security. However, static analysis has its limits, particularly when dealing with complicated codebases, even if it is still a powerful tool for finding vulnerabilities via code review [10]. On the other side, dynamic analysis is very effective in finding flaws in a running programme, however it does not come without its own difficulties.

Evidence from real-world incidents like the Heartbleed flaw and the Equifax hack demonstrates the need of these safeguards. These cases illustrate why a unified strategy for application security is essential, one that draws on the best features of both static and dynamic analysis techniques. Organizations should think about a comprehensive security plan that is guided by relevant theories and best practices in order to successfully preserve sensitive data and limit the likelihood of significant security events.

We will next expand upon this foundation by doing a comprehensive comparison of static and dynamic analytic techniques as part of our research project [6]. In addition to assessing their independence, this research will look for ways in which they might work together to improve application security.

Research Methodology

Plan for Research

• Comparative Analysis:

This study utilizes a comparative research approach to compare and contrast the efficacy of static and dynamic analysis methods for discovering security flaws in software programs. a. This method compares the two methods side by side to learn more about their advantages, disadvantages, and usefulness in various settings. Accuracy, speed, coverage, and practicality are just few of the factors that will be evaluated in this comparison study. Questions like "when does one technique outperform the other?" and "how do they complement each other in improving application security?" are targeted for analysis. This method provides a thorough comprehension of the usefulness of both static and dynamic analysis in various settings.

• Mixed Methods:

This study utilizes a mixed-methods strategy to thoroughly assess both static and dynamic analytic methodologies. The study topic is examined from several angles using this method, which incorporates both quantitative and qualitative techniques. The number of vulnerabilities found and the percentage of false positives are only two examples of the quantitative data that will be used in the study (Dencheva, 2022). Exploring and interpreting the qualitative features in great detail, including the practical consequences of vulnerabilities found by each approach, is what qualitative analysis is all about. Using a variety of approaches, this study hopes to give a comprehensive evaluation of static and dynamic analyses' relative merits and shortcomings.

Data Gathering

Selection of Applications: A wide range of software applications from different fields will be chosen as the starting point for the study. This selection procedure is crucial to ensure that the results are valid and widely applicable. The sample will contain both free and paid programs, representing a broad range of those actually in use. Reflecting the broad landscape of application security concerns, the variety of applications will aid in assessing static and dynamic analysis methodologies across various software.

Vulnerability Data: Research would be significantly hampered without access to vulnerability data from the past. Various sources of information on attack patterns and known vulnerabilities will be compiled to form a solid basis for the analysis. This information will be collected through government databases, private organizations, and public reports. Research can evaluate the efficacy of static and dynamic analysis methods by compiling historical data on vulnerabilities. It enables the detection of repeated vulnerabilities, the severity of such vulnerabilities, and the actual effects of security breaches. This historical information will be used to compare the effectiveness of various vulnerability detection methods and their ability to spot new threats[17]. Therefore, vulnerability data integration into the research will allow for a solid and well-informed evaluation of static and dynamic analysis methodologies in real-world application security settings.

Static Analysis:

• Static analysis of the source code will be performed with automated tools to look for security holes. Standards and best practices in the field will guide the selection of the tools.

• Code structure will be evaluated and potentially insecure coding patterns will be uncovered using an AST-based analysis.

• Input validation and data leakage will be the primary areas of attention when data flow analysis is used to analyze how information is handled in the code.

Dynamic Analysis:

• Dynamic analysis will employ runtime testing techniques to mimic real-world circumstances and find vulnerabilities connected to the behavior of the program while it is being executed.

• Testing the application's resilience to exploitation using ethical hacking techniques, with a focus on discovering runtime vulnerabilities. b. Penetration Testing.

• Fuzz testing, or input validation and error handling, will be evaluated.

Comparative Analysis

Accuracy, runtime, coverage, and practical applicability are only few of the metrics that will be used to assess the efficacy of static and dynamic analysis methods. The study will compare and contrast the methods, taking into account the advantages and disadvantages of each in various settings.

Combine Theories and Ideas:

Concepts and theories from software security, vulnerability assessment, and risk mitigation will be woven into the study as a whole. Results will be analyzed and interpreted using the "attack surface" idea, "security hygiene" principles, and the "CIA triad" in mind.

Project Management

To guarantee that the project's important milestones are completed, resources are distributed efficiently, and any risks or constraints are identified and dealt with, thorough project management is required. The entire project will take 16 weeks, during which time the following will occur:

Explanation of Methods

Analytical Statics

Methodology Using static analysis tools like Checkmarx and Fortify, which are widely used in the industry.

Languages: Looking at Python, C++, and Java source code.

Evaluation of Change

Using well-known dynamic analysis tools like Wireshark and Burp Suite as examples.

We use JavaScript, PHP, and Ruby to test web and desktop apps.

Milestones

Project kickoff, research proposal writing, and team building in weeks 1-2.

Three to four weeks should be spent doing a thorough literature study to lay the groundwork.

Data collection and software selection occur throughout weeks 5 and 6.

During Weeks 7-8, you'll do static analysis like code reviews and AST analysis.

Dynamic analysis, which includes runtime testing and penetration testing, takes place in weeks 9 and 10.

11and 12 week activities include data analysis, metric review, and use case identification.

Weeks 13 and 14 focus on putting software security principles and theories into practise.

Weeks 15-16: Report writing, wrapping up loose ends, and looking forward at potential expansion.

Risk Assessment and Matrix

Initiation of Project (Weeks 1-2)

• Establish the goals and parameters of the project.
• Create a research proposal that details your study question and approach.
• Gather the relevant research personnel.
• Locate and assign resources, such as computers with the appropriate software and analytical tools.

Review of Literature (Weeks 3–4)

• Research the use of static and dynamic analysis methods for securing applications by reading the related literature.
• The study design relies on a summary and analysis of the relevant literature.

Information Gathering (Weeks 5 & 6)

• Choose an array of programs from which to draw conclusions, making use of both free and paid programs.
• Gather vulnerability information from security and vulnerability databases that goes back in time.
• Get all the data together so it can be analyzed.

Static Analysis (Weeks 7-8)

• Methods of static analysis such as code reviews, AST analyses, and data flow analyses should be put into action.
• Applying static analysis techniques to the chosen applications, document your findings.
• Note down any difficulties or restrictions experienced throughout the static analysis process.

Evaluation of Change (Weeks 9-10)

• Dynamic analysis methods like as runtime testing, penetration testing, and fuzz testing should be used.
• Run dynamic analysis on the selected apps and keep track of the data.
• Think about how you may use dynamic analysis in the actual world and evaluate its merits and drawbacks.

Analysis of Data (Weeks 11 and 12)

• Evaluate the static and dynamic findings side by side.
• Evaluate how each method performs in terms of precision, velocity, scope, and practical applicability.
• Figure out when one method is superior to the other and how the two can work together.

Applying Knowledge(Weeks 13 and 14)

• Apply theories and frameworks for software security, risk assessment, and vulnerability analysis to the investigation.
• Apply these ideas and theories to the study you've conducted.

Synopsis and Final Thoughts(Weeks 15-16)

• Create a detailed report outlining your results.
• Use the results of the research to draw conclusions and propose concrete steps to improve application security.
• Create a presentation that encapsulates the findings of the study.

Potential Risks and Limitations

• Resource Restriction: One such threat is the lack of availability of necessary software or specialized analytical tools. This limitation may restrict the scope of the study by reducing the number of accessible apps for analysis and perhaps biassing the results in favor of those applications.

• Data Availability is a potential source of bias in the study because it uses previous vulnerability data. Vulnerability assessments and the generalizability of conclusions may be compromised by missing or biassed data. It may also be difficult to undertake a complete examination of specific vulnerabilities due to a lack of data.

• Thirdly, the project has a strict 16-week deadline. However, the depth of study for a large number of applications may be constrained by this timescale, even while it provides for a full investigation of a decent number of applications. Practical considerations require adherence to the set timeline, even though a longer study period can yield more in-depth insights.

• Responsible disclosure of vulnerabilities raises ethical questions that might affect how researchers conduct their studies. Ethical considerations concerning when, how, and to whom vulnerabilities in software applications should be informed arise whenever a security hole is discovered in a program. The research's credibility and the participation of relevant stakeholders might be jeopardized if these ethical concerns are ignored.

Mitigation Strategies

Several methods will be used in the study effort to deal with these potential problems and constraints:

• The project will prioritize picking a varied sample of software applications in order to deal with limited resources. This variety will include both well-known and lesser-known programs, as well as a wide range of subject areas and software licenses. By taking this tack, we can be confident that our conclusions won't be unduly dependent on just one or two use cases.

• Second, we'll make an attempt to confirm the historical vulnerability data we utilized in the research, which should help with data availability difficulties. Any discrepancies or biases in the data will be noted and taken into account before any conclusions are drawn.

• Given the time limits, effective time management and meticulous preparation are required. To make the most efficient use of time, the project will lay up a detailed schedule with specific goals and checkpoints. Reviewing work at regular intervals can assist find any snags and make any necessary modifications.

• Complying with ethical standards is of the utmost importance and will be maintained throughout the study. The research team will always act ethically, especially when it comes to the disclosure of security flaws. Ethical integrity of the project and stakeholder collaboration may be maintained by open and responsible reporting of findings.

Ethical Implication

There are a number of moral issues that must be carefully addressed throughout this examination of static and dynamic application security techniques:

• If the research involves human participants, such as the creators or users of the chosen applications, it is crucial to first gain their informed consent. In order for participants to make educated judgments about taking part in a research, they need to know its purpose, any risks involved, and their rights.

• When vulnerabilities are uncovered through study, ethical considerations about responsible disclosure arise. Ethical criteria for disclosing vulnerabilities should be followed by researchers so that owners or maintainers of vulnerable software are informed in a timely manner.

• Researches must adhere to privacy and data protection requirements when gathering and analyzing data, especially vulnerability data from the past. Anonymizing and carefully handling personal information is necessary to protect people's right to privacy.

• Researchers should work to remain objective and avoid making assumptions that might influence their findings. It is essential that the strengths and limitations of static and dynamic analysis methods be reported and analyzed objectively.

• The research process should be open and accountable to the public. To maintain the research's credibility and enable for examination by the scientific community, thorough documentation of methods, tools, and results is required.

• Researchers should declare any conflicts of interest, such as financial ties to hardware or software manufacturers or participation in organizations that stand to gain or lose from the study's findings. The credibility of the study depends on complete openness in this regard.

• Ethical Compliance All research must strictly comply with institutional ethical guidelines and standard industry practices. Researchers should carry out the study with the utmost honesty and expertise, according to these ethical guidelines.

Respecting the rights and well-being of individuals and organizations is a top priority for the research, and by addressing these ethical implications, it hopes to preserve its ethical integrity, encourage responsible research conduct, and provide significant insights to the area of application security.

References

[1] Bogović, Slavica, Zoran Stjepanovič, Andrej Cupar, Simona Jevšnik, Beti Rogina-Car, and Andreja Rudolf. "The use of new technologies for the development of protective clothing: comparative analysis of body dimensions of static and dynamic postures and its application." Autex Research Journal 19, no. 4 (2019): 301-311.

[2] Zhu, Guohua, Jiapeng Liao, Guangyong Sun, and Qing Li. "Comparative study on metal/CFRP hybrid structures under static and dynamic loading." International Journal of Impact Engineering 141 (2020): 103509.

[3] Banitalebi Dehkordi, Afsaneh, MohammadReza Soltanaghaei, and Farsad Zamani Boroujeni. "The DDoS attacks detection through machine learning and statistical methods in SDN." The Journal of Supercomputing 77 (2021): 2383-2415.

[4] Ferrag, Mohamed Amine, Leandros Maglaras, Sotiris Moschoyiannis, and Helge Janicke. "Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study." Journal of Information Security and Applications 50 (2020): 102419.

[5] Hady, Anar A., Ali Ghubaish, Tara Salman, Devrim Unal, and Raj Jain. "Intrusion detection system for healthcare systems using medical and network data: A comparison study." IEEE Access 8 (2020): 106576-106584.

[6] Dencheva, Lyubka. "Comparative analysis of Static application security testing (SAST) and Dynamic application security testing (DAST) by using open-source web application penetration testing tools." PhD diss., Dublin, National College of Ireland, 2022.

[7] Yuan, Hongli, Yongchuan Tang, Wenjuan Sun, and Li Liu. "A detection method for android application security based on TF-IDF and machine learning." Plos one 15, no. 9 (2020): e0238694.

[8] Kaur, Arvinder, and Ruchikaa Nayyar. "A comparative study of static code analysis tools for vulnerability detection in c/c++ and java source code." Procedia Computer Science 171 (2020): 2023-2029.

[9] Mateo Tudela, Francesc, Juan-Ramon Bermejo Higuera, Javier Bermejo Higuera, Juan-Antonio Sicilia Montalvo, and Michael I. Argyros. "On Combining Static, Dynamic and Interactive Analysis Security Testing Tools to Improve OWASP Top Ten Security Vulnerability Detection in Web Applications." Applied Sciences 10, no. 24 (2020): 9119.

[10] Zhu, Guohua, Jiapeng Liao, Guangyong Sun, and Qing Li. "Comparative study on metal/CFRP hybrid structures under static and dynamic loading." International Journal of Impact Engineering 141 (2020): 103509.

[11] Kilincer, Ilhan Firat, Fatih Ertam, and Abdulkadir Sengur. "Machine learning methods for cyber security intrusion detection: Datasets and comparative study." Computer Networks 188 (2021): 107840.

[12] Javed, Farhana, Muhamamd Khalil Afzal, Muhammad Sharif, and Byung-Seo Kim. "Internet of Things (IoT) operating systems support, networking technologies, applications, and challenges: A comparative review." IEEE Communications Surveys & Tutorials 20, no. 3 (2018): 2062-2100.

[13] Kollnig, Konrad, Anastasia Shuba, Reuben Binns, Max Van Kleek, and Nigel Shadbolt. "Are iphones really better for privacy? comparative study of ios and android apps." arXiv preprint arXiv:2109.13722 (2021).

[14] Wang, Haoyu, Zhe Liu, Jingyue Liang, Narseo Vallina-Rodriguez, Yao Guo, Li Li, Juan Tapiador, Jingcun Cao, and Guoai Xu. "Beyond google play: A large-scale comparative study of chinese android app markets." In Proceedings of the Internet Measurement Conference 2018 , pp. 293-307. 2018.

[15] Sharma, Surbhi, and Baijnath Kaushik. "A survey on internet of vehicles: Applications, security issues & solutions." Vehicular Communications 20 (2019): 100182.

[16] Ferrag, Mohamed Amine, Leandros Maglaras, Sotiris Moschoyiannis, and Helge Janicke. "Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study." Journal of Information Security and Applications 50 (2020): 102419.

[17] Cai, Haipeng, Na Meng, Barbara Ryder, and Daphne Yao. "Droidcat: Effective android malware detection and categorization via app-level profiling." IEEE Transactions on Information Forensics and Security 14, no. 6 (2018): 1455-1470.

[18] Ramadan, H. S., Mohamed Becherif, and Frédéric Claude. "Extended kalman filter for accurate state of charge estimation of lithium-based batteries: a comparative analysis." International journal of hydrogen energy 42, no. 48 (2017): 29033-29046.

[19] Vinayakumar, R., Mamoun Alazab, K. P. Soman, Prabaharan Poornachandran, and Sitalakshmi Venkatraman. "Robust intelligent malware detection using deep learning." IEEE access 7 (2019): 46717-46738.

[20] Zhang, Lijun, Hui Peng, Zhansheng Ning, Zhongqiang Mu, and Changyan Sun. "Comparative research on RC equivalent circuit models for lithium-ion batteries of electric vehicles." Applied Sciences 7, no. 10 (2017): 1002.

[21] Sharifzadeh, Mahdi, Alexandra Sikinioti-Lock, and Nilay Shah. "Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression." Renewable and Sustainable Energy Reviews 108 (2019): 513-538.

[22] Bharadiya, Jasmin Praful. "A Comparative Study of Business Intelligence and Artificial Intelligence with Big Data Analytics." American Journal of Artificial Intelligence 7, no. 1 (2023): 24.

[23] Pollitt, Christopher, and Geert Bouckaert. Public management reform: A comparative analysis-into the age of austerity . Oxford university press, 2017.

[24] Tran, Manh-Kien, Andre DaCosta, Anosh Mevawalla, Satyam Panchal, and Michael Fowler. "Comparative study of equivalent circuit models performance in four common lithium-ion batteries: LFP, NMC, LMO, NCA." Batteries 7, no. 3 (2021): 51.

[25] Mahfouz, Ahmed, Tarek M. Mahmoud, and Ahmed Sharaf Eldin. "A survey on behavioral biometric authentication on smartphones." Journal of information security and applications 37 (2017): 28-37.

[26] Alzaylaee, Mohammed K., Suleiman Y. Yerima, and Sakir Sezer. "DL-Droid: Deep learning based android malware detection using real devices." Computers & Security 89 (2020): 101663.

[27] Martínez, Jesús González, Asia Torres Pérez, María Gijón Vega, and Teresa Nuñez-Villaveiran. "Preoperative vascular planning of free flaps: comparative study of computed tomographic angiography, color Doppler ultrasonography, and hand-held Doppler." Plastic and reconstructive surgery 146, no. 2 (2020): 227-237.

[28] Alahmadi, Dimah H., Fatmah Abdulrahman Baothman, Mona M. Alrajhi, Fatimah S. Alshahrani, and Hawazin Z. Albalawi. "Comparative analysis of blockchain technology to support digital transformation in ports and shipping." Journal of Intelligent Systems 31, no. 1 (2022): 55-69.

[29] Du, Wei, Zhe Chen, Kevin P. Schneider, Robert H. Lasseter, Sai Pushpak Nandanoori, Francis K. Tuffner, and Soumya Kundu. "A comparative study of two widely used grid-forming droop controls on microgrid small-signal stability." IEEE Journal of Emerging and Selected Topics in Power Electronics 8, no. 2 (2019): 963-975.

[30] Vinayakumar, R., K. P. Soman, Prabaharan Poornachandran, and S. Sachin Kumar. "Detecting Android malware using long short-term memory (LSTM)." Journal of Intelligent & Fuzzy Systems 34, no. 3 (2018): 1277-1288.

You Might Also Like:

Research Proposal Writing Help

Couldn’t Craft A Winning Research Proposal? Here Is How You Can!

Data Science Word Embedding