This assignment develops essential research and source evaluation skills by guiding students to locate and assess credible resources for a chosen topic. By completing this task, students will enhance their ability to critically evaluate information and document findings in APA format.

Students will:

Select a research topic and plan a query using effective keywords.

Use the OneSearch library tool to identify and refine relevant resources.

Evaluate two selected sources using the Source Evaluation Guide.

Summarize their findings in an APA$-$formatted report, reflecting on the research process.

Example Submission

Analyzing Ocean Wave Patterns to Improve

Maritime Safety

Student Name

Research and Source Evaluation

COMP$-1702$: Introduction to Data Science and Machine Learning

RRC Polytech

Date

Topic Statement:

I wanted to explore how predictive analytics can improve maritime safety through analyzing

ocean wave patterns and vessel movements. As someone studying DSML and a big fan of the

ocean, I found this particularly interesting.

Query:

This helped me narrow down to truly relevant sources.

Search Results Overview:

I noticed some interesting patterns in how this field is developing:

Started with "predictive analytics" combined with "ocean waves" OR "wave patterns"

Added terms like maritime safety and vessel movements to focus the results

Applied filters: $2019-2024,$English$,$ Academic Journals, Peer$-$reviewed only

My search revealed $15$relevant sources:

$8$Journal Articles

$4$IEEE Conference Papers

$3$Technical Reports

Recent papers $(2021-2024)$heavily utilize AI and ML approaches

Earlier works $(2019-2020)$focus more on statistical methods

Most research emphasizes practical implementation

Strong trend toward combining multiple data sources

Links to Resources:

$1.$Characterization and Edge$-$Centric Predictive Modeling in an Ocean Network IEEE Access

$(2023)$

$2.$Application of an Analytic Methodology to Estimate the Movements of Moored Vessels Water

Journal $(2019)$

Source Evaluation:

First Source:

Second Source:

Through these sources, I could see how predictive analytics is actually being used to make

maritime operations safer $-$from theoretical models to real$-$world applications as shown below.

Relevance: The paper uses current DSML techniques for maritime safety. It caught my

attention because it shows how modern analytics can solve real problems.

Authority: Published in IEEE Access, which is highly respected in technology fields. The

authors are experts in maritime technology.

Accuracy: They clearly showed their testing methods and validated their results. Their

approach used Bayesian frameworks and hybrid learning methods.

Purpose: Their goal was to improve maritime safety through better prediction systems $-$

they actually achieved improved prediction accuracy in their tests.

Relevance: This study analyzed $27$real vessels over $18$months $-$exactly the kind of

practical application I was looking for.

Authority: The research was implemented by actual port authorities and proved

successful in real operations.

Accuracy: They used three different measurement systems to ensure accurate data

collection. Their results showed impressive prediction rates $($R$^2=0\mathrm{.}71$for some

movements$).$

Purpose: The study aimed to make ports safer by predicting vessel movements more

accurately, and it's now being used in real port operations.

Research Insights

During my research, I came upon some fascinating developments in maritime safety

technology. The IEEE study showcased how modern predictive analytics are being utilized to

enhance port safety. They've developed smart computer systems that can anticipate how ships

will react to different ocean conditions. What's particularly interesting is how they've melded

traditional maritime knowledge with new data science techniques.

The second study brought these ideas from theory into the real world. By observing $27$ships

over an $18-$month period, they demonstrated that these predictions are practical. They used

three different measurement systems $$including specialized cameras and sensors $$to

monitor ship movements. The most exciting finding was their ability to predict certain ship

movements with $71\%$accuracy$.$ This means ports can now better foresee potentially dangerous

situations before they arise.

Together, these studies highlight how data science is driving real improvements in maritime

safety. It's not just theoretical anymore$$ports are actively using these systems to make better

decisions about ship movements and safety procedures.