Tag Archives: provide

CAN YOU PROVIDE MORE EXAMPLES OF CAPSTONE PROJECTS IN DIFFERENT DISCIPLINES AT UCF

Leave a reply

Engineering Capstone Projects:

Computer Engineering: A group of computer engineering students developed a smart home automation system using Raspberry Pi microcontrollers and Python programming. The system allowed users to control lights, thermostats, locks and other devices in their home remotely via a mobile app. It utilized sensors to trigger automated actions like turning lights on at dusk. The project demonstrated skills in embedded systems, networking, software design and integration of IoT devices.

Civil Engineering: A team of civil engineering students designed and proposed plans for improving traffic flow at a congested intersection near the UCF campus. They conducted traffic counts at different times of day, analyzed accident data, and used computer modeling software to simulate potential design solutions like adding turn lanes, changing signal timing or realigning the intersection. Their final design included widening one of the roads to add a left turn lane as well as adjusting signal phases based on time of day traffic patterns.

Mechanical Engineering: For their capstone, mechanical engineering students developed a prototype robotic arm to assist in manufacturing processes. They designed each segment and joint of the arm using 3D modeling software. The arm included sensors to provide position feedback and was programmed to follow pre-defined trajectories for picking, placing and assembling parts. The students tested torque and speed capabilities of motor choices, and integrated an HMI user interface. Their prototype demonstrated the robotic arm’s potential for automating repetitive manufacturing tasks.

Biomedical Sciences Capstone Projects:

Biomedical Sciences: A group of biomedical sciences students analyzed gene expression data from cancer tissue samples to identify potential biomarkers for prognosis or prediction of treatment response. They pre-processed raw data files, conducted statistical analyses in R to find differentially expressed genes between cancer types or disease stages. Candidate biomarkers were validated using additional external data sets. Their findings provided insights toward precision medicine approaches for personalized cancer treatment.

Microbiology: For their capstone, microbiology students investigated antibiotic resistance genes present in bacteria isolated from a local lake. They designed PCR primers to detect various resistance genes and applied DNA extraction, amplification and gel electrophoresis techniques. Whole genome sequencing was also used to examine genomic context of identified resistance genes. Analysis showed the environmental bacteria harbored several clinically-relevant resistance genes, providing information on resistance dissemination and calling for prudent antibiotic use.

Health Sciences: A group of health sciences students focused their capstone on improving mental health and wellness services for college students. They conducted needs assessment surveys and focus groups on campus to understand barriers to care. Based on their findings, they proposed recommendations including expanding counseling center hours, adding peer support groups, incorporating mental health education into coursework. They developed an outreach plan and wellness workshop curriculum to promote mental health awareness and help-seeking among students.

Social Sciences Capstone Projects:

Psychology: For their capstone, psychology students conducted an original research study on the impact of social media usage on well-being and self-esteem in college students. They developed measures of social media engagement, life satisfaction, and Rosenberg Self-Esteem scales to survey a sample of undergraduates. Using SPSS, they analyzed relationships between variables and differences between groups. Findings provided insight on effective social media usage and highlighted needs for education on maintaining wellness in the digital age.

Legal Studies: A group of legal studies students selected a controversial recent U.S. Supreme Court case and analyzed key legal issues, opinions, dissenting views and potential societal impacts. They researched precedent cases, constitutional principles, and scholarly evaluations of the ruling. For their capstone project, they hosted a moot court role-playing the oral arguments before the Supreme Court. As justices, lawyers and observers, they demonstrated understanding of complex legal analysis and the court system.

Sociology: For their capstone, sociology students conducted in-depth interviews with local nonprofit leaders and analyzed community needs assessments to identify an underserved group in the Orlando area. They developed a strategic plan and grant proposal for a new nonprofit initiative to address transportation barriers faced by low-income residents. Their work demonstrated research, assessment, and program development skills in applying a sociological lens to a real-world issue.

As these examples illustrate, capstone projects across different UCF disciplines provide opportunities for hands-on, real-world experience applying technical and analytical skills to address meaningful problems. Students demonstrate abilities to design innovative solutions, conduct research, and develop detailed proposals or prototypes – gaining experience vital for post-graduate careers or further study. The capstone serves as a culminating demonstration of what students have learned during their academic programs.

CAN YOU PROVIDE MORE DETAILS ON THE SPECIFIC DATA TRANSFORMATIONS THAT NEED TO BE PERFORMED

Leave a reply

Data cleaning and validation: The first step involves cleaning and validating the data. Some important validation checks include:

Check for duplicate records: The dataset should be cleaned to remove any duplicate sales transactions. This can be done by identifying duplicate rows based on primary identifiers like order ID, customer ID etc.

Check for missing or invalid values: The dataset should be scanned to identify any fields having missing or invalid values. For example, negative values in quantity field, non-numeric values in price field, invalid codes in product category field etc. Appropriate data imputation or error correction needs to be done.

Outlier treatment: Statistical techniques like Interquartile Range can be used to identify outlier values. For fields like quantity, total sales amount – values falling outside 1.5 IQR from upper and lower quartiles need to be investigated. Appropriate corrections or exclusions need to be made.

Data type validation: The data types of fields should be validated against the expected types. For example, date fields shouldn’t contain non-date values. Appropriate type conversions need to be done wherever required.

Check unique fields: Primary key fields like order ID, customer ID etc should be checked to not contain any duplicate values. Suitable corrections need to be made.

Data integration: The cleaned data from multiple sources like online sales, offline sales, returns etc need to be integrated into a single dataset. This involves –

Identifying common fields across datasets based on descriptions, metadata. For example – product ID, customer ID, date fields would be common across most datasets.

Mapping different name/codes used for same entities in different systems. For example, different product codes used by online vs offline systems.

Resolving conflicts if same ID represents different entities across systems or if multiple IDs map to same real world entity. Domain knowledge would be required.

Harmonizing datatype definitions, formatting and domains across systems for common fields. For example, standardizing date formats.

Identify related/linked records across tables using primary and foreign keys. Append linked records rather than merging wherever possible to avoid data loss.

Handle missing field values which are present in one system but absent in other. Appropriate imputation may be required.

Data transformation and aggregation: This involves transforming the integrated data for analysis. Some key activities include:

Deriving/calculating new attributes and metrics required for analysis from base fields. For example, total sales amount from price and quantity fields.

Transforming categorical fields into numeric for modeling. This involves mapping each category to a unique number. For example, product category text to integer category codes.

Converting date/datetime fields into different formats needed for modeling and reporting. For example, converting to just year, quarter etc.

Aggregating transaction-level data into periodic/composite fields needed. For example, summing quantity sold by product-store-month.

Generating time series data – aggregating sales by month, quarter, year from transaction dates. This will help identify seasonal/trend patterns.

Calculating financial and other metrics like average spending per customer, percentage of high/low spenders etc. This creates analysis-ready attributes.

Discretizing continuous valued fields into logical ranges for analysis purposes. For example, bucketing customers into segments based on their spend.

Data enrichment: Additional contextual data from external sources is integrated to make the sales data more insightful. This includes:

Demographic data about customer residence location to analyze regional purchase patterns and behaviors.

Macroeconomic time series data about GDP, inflation rates, unemployment rates etc. This provides economic context to sales trends over time.

Competitor promotional/scheme information integrated at store-product-month level. This may influence sales of same products.

Holiday/festival calendars and descriptions. Sales tend to increase around holidays due to increased spending.

Store/product attributes data covering details like store size, type of products etc. This provides context for store/product performance analysis.

Web analytics and CRM data integration where available. Insights on digital shopping behaviors, responses to campaigns, churn analysis etc.

Proper documentation is maintained throughout the data preparation process. This includes detailed logs of all steps performed, assumptions made, issues encountered and resolutions. Metadata is collected describing the final schema and domain details of transformed data. Sufficient sample/test cases are also prepared for modelers to validate data quality.

The goal of these detailed transformation steps is to prepare the raw sales data into a clean, standardized and enriched format to enable powerful downstream analytics and drive accurate insights and decisions. Let me know if you need any part of the data preparation process elaborated further.

CAN YOU PROVIDE SOME EXAMPLES OF INTERDISCIPLINARY TOPICS THAT COULD BE USED FOR A TEXTBOOK CAPSTONE PROJECT

Leave a reply

Climate change is an issue that lends itself well to an interdisciplinary approach as it involves both natural science aspects like environmental science and also social implications. A project exploring how climate change will impact various areas of life could touch on the scientific projections for things like rising sea levels, increased extreme weather events, altered agricultural growing patterns, etc. It could then discuss the societal and economic implications of those changes. For example, how will coastal cities and communities be affected by sea level rise, what agricultural communities may be impacted, how will infrastructure need to adapt. It allows exploration of both the scientific drivers and causes of climate change as well as the human impact. This would require research across fields like environmental science, sociology, economics, urban planning, and more.

Another option is to focus on a topic related to sustainability from an interdisciplinary lens. This could look at making communities, cities, or systems more environmentally, socially, and economically sustainable. Areas of focus could include development that meets current needs without compromising future generations, green energy and infrastructure, sustainable food systems, circular economies, conservation, equitable access to resources, etc. Research would come from disciplines like environmental science, engineering, urban planning, economics, business, and ethics. Case studies could be examined to understand successful sustainable development initiatives and strategies used. Challenges, tradeoffs, and innovative solutions across sectors would provide a rich understanding of creating truly sustainable systems.

Mental health is another area that lends itself to interdisciplinary study. A capstone project could explore topics like the influence of societal and environmental factors on mental health outcomes. Research from fields such as psychology, sociology, public health, urban planning, and more could be synthesized to develop a holistic understanding. For example, the links between lack of access to services, poverty, social determinants of health, urban design features, and rates of mental health issues like depression, anxiety, and schizophrenia in particular populations. Promising prevention and intervention strategies could then be evaluated through an interdisciplinary lens. Policy approaches, community programs, medical treatment models and how factors like social connections, income, green space, all impact mental health present an opportunity to study interrelated solutions across disciplines.

The societal impacts of artificial intelligence is another area ripe for interdisciplinary investigation. A textbook capstone could explore topics such as the development of AI and machine learning techniques from a computer science perspective, while also examining the automation of jobs and changes to the labor market through an economics lens. Sociological study of shifts in necessary job skills and social connections could be included. Potential civil and ethical issues regarding data privacy, algorithmic bias, and accessibility present opportunities for investigation involving law, ethics and social justice. Looking at proposals for regulating AI and mitigating societal harms interweaves technology, governance and social domains. Case studies of current AI applications and their influence on different sectors, from transportation to education to healthcare, allow significant depth exploring relationships across boundaries.

One other example of an interdisciplinary topic area is that of pandemics and global health issues. Studying infectious disease outbreaks and how to prepare for future pandemics involves epidemiology, virology, and public health. It also relates to social and political aspects through issues like health communication strategies, medical countermeasure development, balancing individual civil liberties with societal safety, and international coordination. Additional fields like behavioral science and ethics come into play regarding maximizing voluntary prevention behaviors and equitable allocation of scarce resources during crises. Economic impacts and recovery considerations touch on multiple domains as well. This offers an opportunity to holistically analyze complex, system-wide pandemic mitigation and response strategies across scientific and social realms. Particular outbreaks like COVID-19 or influenza could supply case-based depth.

Issues involving climate change, sustainability, mental health, artificial intelligence, and pandemics present compelling options for interdisciplinary textbook capstone projects. They offer the potential to deeply explore topics at the intersection of multiple fields by synthesizing diverse research perspectives. Case studies can provide real-world examples to help illustrate interrelationships between scientific and social factors. The multi-dimensional nature of these kinds of issues lends itself to fulfilling the goal of an interdisciplinary approach encompassing over 15,000 characters of thorough detail analyzing topics across boundaries of traditional academic silos.

CAN YOU PROVIDE SOME TIPS ON HOW TO SELECT A TOPIC FOR A CAPSTONE PROJECT

Leave a reply

Choose a topic that you are genuinely interested in. Your capstone project will require a significant time commitment, so you want to ensure you have a personal interest in your topic to stay motivated throughout the entire process. Picking a topic just because you think your professors or committee will like it is not a good strategy. You need to be fascinated by the subject matter to sustain your energy.

Consult with your capstone advisor or committee members. Have informal conversations with the faculty members who will be overseeing your project. Explain what topics initially interest you and get their input on feasibility and potential directions for exploration within those topic areas. They can shed light on what has or hasn’t been studied before and point you towards resources. Listen to their advice on choosing a focused scope that is ambitious yet realistic to complete within your timeframe.

Scan recent research literature in your field. Conduct preliminary searches of academic databases, journals, and published capstone papers to get a sense of current trends and debates within potential topic domains. Look for gaps in the existing literature or areas that would benefit from further study. You don’t want to simply replicate what has already been done. Choosing a topic at the forefront of new developments will better showcase your abilities.

Consider relevance to your future career goals. Opt for a subject that will not just satisfy your program requirements but also look impressive on your resume and help you network in your intended career sector after graduation. Your capstone provides an opportunity to explore a topic closely tied to your vocational aspirations. Focusing on a specific issue, method or case study relevant to your industry can attract employer attention.

Check if necessary resources are accessible. Before committing to an idea, inventory what research materials, datasets, software tools, organizations or case studies you may need to complete an in-depth project. A topic is not feasible if required access is restricted or resources don’t exist. Consult libraries and databases to verify information availability. You may need to tweak your focus if essential primary sources cannot be obtained.

Test potential interest from an audience perspective. Your work should contribute insightful conclusions or applications. Consider if results would likely hold value for peers, practitioners or the general public. Selecting a highly specialized topic that only speaks to a tiny niche may limit readers and the ability to present your findings to broader conferences in the future. Consider issues that could engage non-specialists too for more impactful dissemination.

Discuss options with other students. Classmates conducting similar projects can offer insight from their preliminary research and give you an outside perspective on what they see as the strengths and limitations of your various topic ideas. Brainstorming as a group can spark new directions by building on each other’s interests and expertise. Working through initial proposals with peers provides alternative viewpoints valuable for selection.

Narrow your focus progressively. Start broadly and progressively refine potential topics using the above guidance. Whittle your list down from 3-5 general areas of interest into 1-2 specific research questions or problem statements that can be thoroughly addressed at the depth expected. A clearly defined, nuanced approach is essential for formulating aims, methodology and organization as you begin researching and writing in earnest.

Be open-minded yet decisive. Gather many opinions but avoid endlessly debating options or changing paths. Settle on a single workable topic and then fully commit to exploring it. Perfection is rarely attained in initial plans, so pick one that energizes you and dive in, making adjustments as needed along the way rather than indefinitely spinning your wheels weighing options. Trust your judgment and move forward once feedback concurs your idea is well-considered and executable.

By following these guidelines, you can systematically evaluate options and settle on a capstone project topic that fully leverages your interests, fits program parameters, contributes meaningful results, and prepares you well for your intended career. With patience and input from experts, selecting the right focus area need not be an overwhelming process but rather an exciting starting point for your culminating academic experience.

CAN YOU PROVIDE MORE DETAILS ON HOW THE GRADIENT BOOSTED TREES ALGORITHM WAS TRAINED AND OPTIMIZED

Leave a reply

Gradient boosted trees (GBT) is an machine learning technique for classification and regression problems which produces a prediction model in the form of an ensemble of weak prediction models, typically decision trees. It builds the model in a stage-wise fashion like other boosting methods do, and it generalizes them by allowing optimization of an arbitrary differentiable loss function. GBT typically demonstrates strong predictive performance and it is used widely in many commercial applications.

The core idea of GBT is to combine weak learners into a single strong learner. It differs from a traditional decision tree algorithm in two key ways:

It builds the trees in a sequential, stage-wise fashion where each successive tree aims to improve upon the previous.

It fit the trees not only on the target but also on the negative gradient of the loss function with respect to the prediction of the previous trees in the ensemble. This is done to directly minimize the loss function.

The algorithm starts with an initial prediction, usually the mean value of the target attribute in the training data (for regression) or the most probable class (for classification). It then builds the trees sequentially as follows:

In the first iteration, it builds a tree that best predicts the negative gradient of the loss function with respect to the initial prediction on the training data. It does so by splitting the training data into regions based on the values of the predictor attributes. Then within each region it fits a simple model (e.g. mean value for regression) and produces a new set of predictions.

In the next iteration, a tree is added to improve upon the existing ensemble by considering the negative gradient of the loss function with respect to the current ensemble’s prediction from the previous iteration. This process continues for a fixed number of iterations or until no further improvement in predictive performance is observed on a validation set.

The process can be summarized as follows:

Fit tree h1(x) to residuals r-1=y-yn=0 where yn=0 is the initial prediction (e.g. mean of y)

Update model: f1(x)=yn=0+h1(x)

Compute residuals: r1=y-f1(x)

Fit tree h2(x) to residuals r1

Update model: f2(x)=f1(x)+h2(x)

Compute residuals: r2=y-f2(x)

Repeat until terminal condition is met.

The predictions of the final additive model are the predictions of the grown trees combined. Importantly, the trees are not pure decision trees but are fit to approximations of the negative gradients – this turns the boosting process into an optimization algorithm that directly minimizes the loss function.

Some key aspects in which GBT can be optimized include:

Number of total trees (or boosting iterations): More trees generally lead to better performance but too many may lead to overfitting. A value between 50-150 is common.

Learning rate: Shrinks the contribution of each tree. Lower values like 0.1 prevent overfitting but require more trees for convergence. It is tuned by validation.

Tree depth: Deeper trees have more flexibility but risk overfitting. A maximum depth of 5 is common but it also needs tuning.

Minimum number of instances required in leaf nodes: Prevents overfitting by not deeply splitting on small subsets of data.

Subsample ratio of training data: Takes a subset for training each tree to reduce overfitting and adds randomness. 0.5-1 is typical.

Column or feature sampling: Samples a subset of features to consider for splits in trees.

Loss function: Cross entropy for classification, MSE for regression. Other options exist but these are most widely used.

Extensive parameter tuning is usually needed due to complex interactions between hyperparmeters. Grid search, random search or Bayesian optimization are commonly applied techniques. The trained model can consist of anywhere between a few tens to a few thousands of trees depending on the complexity of the problem.

Gradient boosted trees rely on the stage-wise expansion of weak learners into an ensemble that directly optimizes a differentiable loss function. Careful hyperparameter tuning is needed to balance accuracy versus complexity for best generalization performance on new data. When implemented well, GBT can deliver state-of-the-art results on a broad range of tasks.