Author Archives: Evelina Rosser

WHAT ARE SOME COMMON EXAMPLES OF CAPSTONE PROJECTS IN DIFFERENT FIELDS OF STUDY?

Leave a reply

Engineering:

A major capstone project for many engineering programs is the senior design project. In this, senior engineering students work in teams to design and build a prototype or functioning product to solve a real-world problem. Some examples of senior design projects include:

Mechanical engineering students designing and building a device to help with material handling or automation of a manufacturing process. Their project would include modeling, prototyping, testing and evaluation.

Electrical/Computer engineering students developing a new hardware or software product. This could be an embedded system, mobile app, website or other technology product. Their project would follow the whole development life cycle from concept to deployment.

Civil engineering students designing and planning the construction of a building, bridge or other infrastructure project. Their project would involve assessing needs, performing calculations and simulations, creating technical drawings and specifications, developing a full construction plan, budget, schedule and addressing any regulatory requirements.

Business:

For business majors, the capstone often consists of a research study or business plan for a new venture. Some examples include:

Marketing students conducting quantitative and qualitative market research into a new product or service idea. This would include identifying target customers, analyzing the competition, assessing demand and developing a full marketing and communications strategy.

Management students writing a comprehensive business plan for launching their own startup company. The plan covers all aspects of launching the venture from market analysis, operations, management team, fundraising needs to projected financials like revenue, costs and profitability over multiple years.

Finance or accounting students performing a detailed financial analysis of a public company. Their project involves researching the industry, valuing the company, conducting ratio analysis of financial statements, and providing investment recommendations based on their findings.

Nursing:

For many nursing programs, the capstone takes the form of a research study or program evaluation within a healthcare setting. Examples include:

Conducting an evidence-based research study on a topic like a new clinical treatment, ways to reduce patient falls in a hospital, or strategies for improving patient education. This would require a literature review, research methods, data collection and analysis and conclusions.

Developing and evaluating a new staff training program, patient screening tool, or community health education program. The project assesses the need, implements the program and measures its outcomes and effectiveness.

Undertaking a process improvement project, for example analyzing hospital readmission rates and developing interventions to reduce readmissions of patients with chronic illnesses. This thoroughly evaluates current processes and ways to integrate practice changes.

Computer Science:

Common computer science capstone projects involve developing substantial software, web or mobile applications to solve problems. Examples include:

Creating a new full-stack web application from scratch like a social network, e-commerce site, or organizational task management system. It requires designing, coding, testing and deploying both the front-end and back-end.

Developing an original mobile app idea with features like geolocation, multimedia, backend integration and more. The app would need to work across different device types and operating systems.

Designing database structures and developing a data analytics or machine learning application involving large datasets. The project aims to extract insights, identify patterns and build predictive models.

Contributing new functionalities or modules to an open source project. This allows students to work on real-world complex codebases while improving an existing product or tool.

The examples shared here represent just a sample of types of substantive, real-world focused capstone projects undertaken across different academic disciplines. A key goal of capstone work is providing students experiential opportunities to integrate and apply the knowledge and skills developed throughout their studies to solve problems or develop products in a hands-on manner. This helps prepare them for professional careers in their respective fields.

CAN YOU EXPLAIN THE PROCESS OF CONDUCTING PRIMARY RESEARCH FOR A CAPSTONE PROJECT?

Leave a reply

Conducting primary research is an essential part of developing a high quality capstone project. Primary research involves collecting original data through methods like surveys, interviews, or experiments specifically designed to address the research topic. The following steps outline the primary research process:

Define the research question and goals. Clearly identify the specific research question or hypothesis you want to explore through primary research. What do you hope to learn or understand better through collecting original data? Having a well-defined research question will help guide the entire research process.

Review relevant literature and previous research. Thoroughly review academic literature and existing research related to your topic to gain background knowledge and see what questions still need to be answered. This literature review will also help identify appropriate research methods and design instruments to collect useful primary data. Comparing your study to existing works will help situate your research within the field.

Select appropriate research methods. Once you understand the existing literature and have a clear research question, you need to decide on research methods that will allow you to collect the necessary data to address your questions. Common qualitative methods for capstone research include surveys, interviews, and focus groups. Quantitative methods include experiments and observational studies. The methodology should directly link to answering the research question.

Develop research instruments. With your methodology selected, the next step is to carefully develop the actual instruments that will be used to collect data, such as survey questions, interview questions or protocols, pre-/post- tests. Your instruments need to be designed to generate high quality, reliable data suitable for analysis. Conduct pilot tests with small samples to identify problems and refine questions before large-scale data collection.

Get necessary approvals. Any research involving human subjects requires approval from your university’s Institutional Review Board to ensure ethical standards are upheld and protect participants. The IRB approval process can take some time, so apply early. You may also need site approval if collecting data off-campus.

Recruit participants and collect data. With approved instruments and protocols in hand, you can begin recruiting appropriate participants for your study based on your research question and methodology. Data collection methods such as surveys or interviews often require making arrangements to meet with participants. Collect comprehensive, high quality data for analysis.

Analyze results. After all your data is collected, the real work of analysis begins. For qualitative data like interviews, analysis involves identifying themes in participants’ responses. Quantitative data requires statistical analysis techniques relevant to your methodology and research question, such as statistical testing. This analysis allows you to draw meaningful conclusions from the primary data collected.

Draw conclusions and discuss implications. Synthesize the results of your analysis and answer key research questions based on the primary data. Your conclusion validates or refutes hypotheses and fills gaps in existing knowledge. Discuss the implications of your findings for theory, practical applications, and directions for future research. Limitations of the methodology should also be addressed.

Present research. The final step is to present your completed research to others. A capstone paper or project allowing for an in-depth report of all aspects of the process from literature review to conclusions based on primary research analysis is an ideal format. You may also have opportunities to present a conference or publish your work. Peer feedback will strengthen presentation of the research.

Conducting methodologically rigorous primary research is a multi-step process requiring careful planning and execution to ensure generation of reliable, meaningful results. Thoroughly following these steps will lead to completion of a high-quality capstone project grounded in original data collection and analysis. Primary research takes significant work but produces valuable new knowledge at the graduate level.

HOW LONG DOES IT TYPICALLY TAKE TO COMPLETE A PROFESSIONAL CAPSTONE PROJECT?

Leave a reply

The amount of time it takes to complete a professional capstone project can vary significantly depending on several factors, but on average students and professionals typically spend between 6-12 months working full-time on their capstone.

Some of the key factors that influence the length of a capstone project include the scope of work, availability of resources and data, methodology required, and other commitments of the student or professional. Capstone projects that involve collecting original data through methods like surveys, interviews, experiments or case studies generally require more time than projects based mostly on secondary data analysis or literature reviews.

For graduate or undergraduate students, capstone projects conducted while also taking classes are usually on the shorter end of 6-9 months. This is because students have other coursework and exams to focus on in addition to their capstone. They may also have limited availability of resources and data due to financial or time constraints. Students who conduct summer research or take a full semester or year off just to focus on their capstone project often have more flexibility and capacity to devote 10-12 months to see the project through from start to finish.

Professionals working on capstones part-time while also maintaining regular full-time employment responsibilities typically aim to complete their projects within 9-12 months. Juggling work, family, coursework if pursuing an advanced degree, and the capstone means professionals have less time available each week to dedicate solely to research and writing. They also have deadlines to meet for graduation or program completion.

Full-time students or professionals who put their regular commitments aside to focus exclusively on the capstone for a set period generally finish sooner, within 6-9 months. This allows for a more immersive experience with longer blocks of uninterrupted time each day/week to optimize productivity. Fewer distractions also enable smoother progress and faster completion of individual tasks and phases of the project lifecycle.

The methodology and scope of work for a capstone also impacts duration. Literature review-based projects examining existing theories and data through synthesis and analysis tend to require 6-9 months. Projects that also demand primary data collection through field work and experiential components may lengthen to 9-12 months to account for recruitment, IRB approval, data gathering, analysis, and interpretation. Capstones involving design and development of new products or programs can often take 10-12 months when factoring in prototyping, testing, iterations and evaluation.

Larger scope projects which aim to solve very complex, open-ended problems through innovative solutions or address challenges spanning multiple contexts/stakeholders usually mandate the full 12 months at a minimum. Analyzing big data sets or conducting extensive qualitative research through numerous interviews also pushes capstones towards the upper duration range. Experimenting with emerging technologies, undertaking systematic reviews, and comparative international studies similarly warrant longer timelines.

Variation also exists depending on individual learning styles, prior experience level, available support structures, self-motivation and time management abilities of the student or professional. Stronger or more experienced researchers tend to work more efficiently while novices may require additional months to consolidate learning. Delays from obstacles like lack of participation, technology issues, need for protocol changes also affect schedules. Capstones focusing on under-researched topics with limited available literature or resources are inherently higher-risk for timeline slippage.

While length may ebb and flow, dedicated capstone committees and advisors help set students up for success by outlining realistic expectations early on. Regular check-ins, milestone tracking and support for time management keep projects on track to meet target completion dates within 6-12 months on average. With prudent planning of objectives, methodology and use of time, most motivated individuals are able to rise above challenges to see their vision through to fruition within this typical capstone project timeframe.

WHAT ARE SOME EXAMPLES OF WEARABLE FITNESS TRACKERS AND CONTINUOUS GLUCOSE MONITORS?

Leave a reply

Fitness Trackers:

Fitbit Charge 5 – One of Fitbit’s most popular trackers, the Charge 5 tracks steps, distance, active minutes and calories burned. It also monitors heart rate, offers exercise modes, sleep tracking and more. It has a color touchscreen display, connects to the Fitbit app and offers features like guided breathing sessions. Battery lasts around 7 days. Retails for around $150.

Apple Watch Series 7 – The latest Apple Watch has a larger display area and faster charging than previous models. It tracks activities, workouts, heart rate, sleep and more. Offers ECG app, fall detection and integration with Apple Fitness+ workouts. Connects to iPhone and various apps. Battery lasts around 18 hours. Pricing starts at $399.

Garmin Vivosmart 5 – A simple, durable tracker from Garmin that monitors steps, distance, sleep, calories and intensity minutes. Heart rate is monitored continuously. Offers relaxation timer, breathing sessions and estimated stress levels. Connects to the Garmin Connect app on phone. Battery lasts 7 days. Around $150.

Samsung Galaxy Watch5 – The latest Galaxy Watch runs Wear OS and offers extensive health/fitness tracking including heart rate, ECG, blood oxygen, body composition, sleep and over 90 workout modes. Has GPS, LTE option, ecobattery modes claims 1.5 days on a charge. Integrates with Samsung Health. Starts around $280.

Xiaomi Mi Smart Band 6 – An affordable basic tracker that monitors steps, calories, distance, sleep, heart rate and offers over 30 exercise modes. Has AMOLED color touch display. connects to Mi Fit app. Can receive call/app notifications. Battery lasts around 14 days. Only $50.

Continuous Glucose Monitors:

Dexcom G6 Continuous Glucose Monitoring System – Considered the top CGM available, the Dexcom G6 displays glucose levels every 5 minutes. Small sensor inserts under the skin and transmits to a receiver/sharing device. Smartphone app where readings are viewable and to set alerts. Sensor lasts 10 days. Requires fingerpricks for calibrations. Around $400/month if not covered by insurance.

Abbott Freestyle Libre 2 – Like the Dexcom, it has a small sensor inserted that lasts 14 days and transmits readings every minute to a reader or smartphone. No finger pricks needed except initial calibration. Provides glucose trend arrows and customizable alerts. Readings accessible via an app. Retails around $75/14 days but costs vary by insurance coverage.

Medtronic Guardian Connect – Considered the most discreet CGM device, it has a small sensor inserted that lasts 6 days and transmits to a separate transmitter clipped to clothes. Readings viewed on smartphone app. Provides custom alerts, thresholds and shares data with healthcare providers. Sensors need to be changed every 6 days. Monthly costs vary by insurance but often over $100/month.

Eversense Continuous Glucose Monitoring System – Unlike other CGMs, the Eversense sensor inside the body lasts 90 days and is inserted under the skin by a health provider. It transmits to a smart transmitter worn on the arm that displays readings. No fingerpricks needed once sensor inserted. Sensor and transmitter replaced every 3 months. Majority of costs often covered by insurance due to longevity.

All CGMs allow diabetics to closely monitor their glucose levels to better manage their diabetes through diet/exercise/medication adjustments based on the continuous readings. This helps avoid dangerous highs and lows. Insurance coverage and costs remain barriers preventing greater access and adoption of this important medical technology for many people with diabetes.

Fitness trackers have become ubiquitous wellness devices in recent years that allow users to easily track their daily activities, exercise, sleep quality and other health metrics from their wrist. While basic trackers just monitor steps, distance, activity etc, higher-end models from Apple, Samsung, Fitbit offer extensive workout tracking options, heart rate monitoring, ECG/EKG functions, stress tracking, sleep analysis and more. The wide array of trackers at various price points has democratized health monitoring for the masses while also sparking healthy competition between tech giants. As new sensors are incorporated, data privacy and regulation remain ongoing concerns as these devices become central hubs of personal wellness information. Both types of devices reviewed here represent important advancements in digital health and personalized, preventative care through constant, 24/7 monitoring of key indicators. As technology improves further and costs decrease, their potential to positively transform global health is vast.

CAN YOU EXPLAIN HOW THE RANDOM FOREST ALGORITHM WORKS IN THE LOAN DEFAULT PREDICTION MODEL?

Leave a reply

Random forest is an ensemble learning algorithm that operates by constructing a multitude of decision trees during training and outputting the class that is the mode of the classes of the individual trees. Random forests correct for decision trees’ tendency to overfit their training set.

The random forest algorithm begins with acquiring a large number of data rows containing information about previous loan applicants and whether they defaulted or repaid their loans. This data is used to train the random forest model. The data would contain features/attributes of the applicants like age, income, existing debt, employment status, credit score etc. as well as the target variable which is whether they defaulted or repaid the loan.

The algorithm randomly samples subsets of this data with replacement, so certain rows may be sampled more than once while some may be left out, to create many different decision trees. For each decision tree, a randomly selected subset of features/attributes are made available for splitting nodes. This introduces randomness into the model and helps reduce overfitting.

Each tree is fully grown with no pruning, and at each node, the best split among the random subset of predictors is used to split the node. The variable and split point that minimize the impurity (like gini index) are chosen.

Impurity measures how often a randomly chosen element from the set would be incorrectly labeled if it was randomly labeled according to the distribution of labels in the subset. Splits with lower impurity are preferred as they divide the data into purer child nodes.

Repeatedly, nodes are split using the randomly selected subset of attributes until the trees are fully grown or until a node cannot be split further. The target variable is predicted for each leaf node and new data points drop down the trees from the root to the leaf nodes according to split rules.

After growing numerous decision trees, which may range from hundreds to thousands of trees, the random forest algorithm aggregates the predictions from all the trees. For classification problems like loan default prediction, it takes the most common class predicted by all the trees as the final class prediction.

For regression problems, it takes the average of the predictions from all the trees as the final prediction. This process of combining predictions from multiple decision trees is called bagging or bootstrapping which reduces variance and helps avoid overfitting. The generalizability of the model increases as more decision trees are added.

The advantage of the random forest algorithm is that it can efficiently perform both classification and regression tasks while being highly tolerant to missing data and outliers. It also gives estimates of what variables are important in the classification or prediction.

Feature/variable importance is calculated by looking at how much worse the model performs without that variable across all the decision trees. Important variables are heavily used for split decisions and removing them degrades prediction accuracy more.

To evaluate the random forest model for loan default prediction, the data is divided into train and test sets, with the model being trained on the train set. It is then applied to the unseen test set to generate predictions. Evaluation metrics like accuracy, precision, recall, F1 score are calculated by comparing the predictions to actual outcomes in the test set.

If these metrics indicate good performance, the random forest model has learned the complex patterns in the data well and can be used confidently for predicting loan defaults of new applicants. Its robustness comes from averaging predictions across many decision trees, preventing overfitting and improving generalization ability.

Some key advantages of using random forest for loan default prediction are its strength in handling large, complex datasets with many attributes; ability to capture non-linear patterns; inherent feature selection process to identify important predictor variables; insensitivity to outliers; and overall better accuracy than single decision trees. With careful hyperparameter tuning and sufficient data, it can build highly effective predictive models for loan companies.