Data Science Graduate Program Student Handbook, Study notes of Database Management Systems (DBMS)

Download Data Science Graduate Program Student Handbook and more Study notes Database Management Systems (DBMS) in PDF only on Docsity!

Data Science Graduate Program

Student Handbook

Last Revised: August 16, 2021 1

Table of Contents

Welcome!

Welcome to the Data Science Graduate Program at Michigan Technological University. The Data Science program is an interdisciplinary program, meaning the faculty and courses for the program coming from all the Colleges across the University. New in 2021-2022 is that the program has a home department in the Computer Science department (part of the College of Computing). Note, the program remains interdisciplinary by design with students taking courses across the university. The degree you seek will be challenging and give you opportunities to learn new skills, practices, and knowledge. The skills and knowledge will be the building blocks of starting a path of lifelong learning in the field of Data Science. The degree program is a course-based curriculum, but you will get involved in many hands-on, real-world activities and projects in these courses. I encourage you all to interact with all your fellow students and faculty. Stretch yourself and work with different students; you will have many opportunities to work in teams, reach up and pair with new students building both your technical skills and team-work and professional skills in the process. This is an opportunity to start building your professional network. The faculty and staff are here to help you succeed. Ask questions, reach out for help. Don’t wait until the end of the semester if you need assistance. This handbook is provided as a document to answer your basic questions. For more information, please refer to the data science website and reach out to your advisor or Data Science director. We wish you great success in the Data Science Graduate Program. Sincerely, Laura E. Brown Director, Data Science Graduate Program

Program Governance

The Data Science program is managed by an inter-disciplinary community of scholars and professional staff working together to support this program. Some of the key personnel include: Dr. Laura E. Brown - Data Science Program Director Home Department, College: Computer Science, College of Computing Office: Rekhi 307, lebrown@mtu.edu Dr. Benjamin Ong - Data Science Executive Committee Home Department, College: Mathematical Sciences, College of Sciences and Arts Office: Fisher 217, ongbw@mtu.edu Dr. Guy Hembroff - Data Science Steering Committee Home Department, College: Applied Computing, College of Computing Director: Health Informatics Graduate Program Office: EERC 311, hembroff@mtu.edu Dr. Jeffrey Wall - Data Science Executive Committee Home Department, College: College of Business Office: AOB G010, jdwall@mtu.edu Dr. Hairong Wei - Data Science Executive Committee Home Department, College: College of Forest Resources and Environmental Science Office: Noblet 176, hairong@mtu.edu Dr. Jianhui Yue - Data Science Executive Committee Home Department, College: Computer Science, College of Computing Office: Rekhi 203, jyue@mtu.edu Most inquiries can be directed towards Dr. Brown. E-mail is the preferred mode of communication.

Graduate Student Government (http://gsg.mtu.edu)

Data Science Representative: Surya Ravula, sravula2@mtu.edu Mr. Ravula will communicate information regarding travel grants, social activities, opportunities and other important information. He can also be used as a contact to communicate suggestions, complaints, and help to answer questions.

For those who were studying during Fall 2020, the following policies impact the program. ● Proposal 30-21 - Extend Time for Completion of Incomplete : The time to complete an “I”, incomplete grade is extended one year past the end of the course. ● Proposal 33-21 - Change Date for Withdrawal with a “W” : Students are allowed to withdraw from a course with a “W” until Friday, December 11th (extended from Friday, Nov. 6th). ● Proposal 37-21 - Pass/Low Pass/ Fail for Fall 2020 : Grades are assigned using the normal grading process. Students will then have seven days to decide if they would like to switch any classes to Pass/Low Pass/Fail grading. Students should talk to their advisors and others on campus about the impact of this change: GPA, course credit, academic standing, degree requirements, financial aid, transfer credit, visas, and acceptance into graduate or professional schools. Impacts of covid-19 on Michigan Tech, will continue into the Spring 2021, pay attention to emails, town halls, the MTU Flex webpage, to learn of the most recent changes.

Getting Started

Listed below are several items to assist you in your orientation at MTU and the Data Science program. Some require your personal attention; others are informational only.

International Programs & Services Office (IPS)

All international students are required to report to International Programs and Services (IPS), Administration Building, Room 200 if you haven’t checked in already. Bring your I-20 or DS-2019, passport and visa.

Housing Information

● On-campus housing information ● Off-campus housing information

Identification Card (HuskyCard)

All students are required to have a HuskyCard for identification and swipe access to buildings, parking lots, and residence halls if applicable. HuskyCards are issued at the HuskyCard Service Center in the IT Service Center, 1st floor of the Van Pelt and Opie Library. A valid government-issued photo ID is required, such as a driver's license, a state ID or a passport.

Office

Office space is only provided for supported GTA/GA/GRAs if required.

After-hours Access

Swipe card after-hours access to the buildings and computer labs will automatically be provided to all enrolled students. If you have been assigned an office space, you will be notified by email when your key is ready to be picked up at Public Safety & Police Services, 206 MacInnes Drive (building 16 on campus map). You will need your MTU ID card (HuskyCard) to pick up your key. If lost, you will be charged $100 for a replacement key.

Parking & Transportation

See the Transportation Services website for detailed information regarding the vehicle registration process, parking fees, and rules/regulations regarding parking. Vehicle registration/parking permit purchase is available online. Bring your vehicle registration and your picture ID to Transportation Services, 100 Administration Building, to pick up your parking permit. During off-hours (4pm-7am weekdays) and all weekend, core campus parking lots and parking meters are open for parking (exception is handicap and designated parking spaces).

Degree Information

The Data Science Masters is a course-based program requiring successful completion of 30 approved credits within five years of starting the program. Specifically, ● 12 credits of core courses must be successfully completed ● at least 6 credits of approved electives must be successfully completed ● at most 6 credits of foundational courses may be taken ● 6 - 12 credits of domain electives may be taken. A passing grade (B or higher) must be obtained in 24 of the above 30 credits; a grade of BC or C may be accepted for the remaining 6 of the 30 credits. Additionally, at least 18 credits must be taken at the graduate level (5xxx and 6xxx).

Core Courses

The following four courses are required for the Data Science degree. These courses are often offered only once a year. You will need to plan accordingly. Fall* UN 5550 Introduction to Data Science MA 5790 Predictive Modeling BA 5200 Information Systems Management and Data Analytics Spring UN 5550** Introduction to Data Science MA 5790*** Predictive Modeling CS 5831 Advanced Data Mining *Note, many students do not need to take all three core courses in their first Fall semester. UN 5550, Introduction to Data Science is recommended for this first semester, but the choice of the other core course should be discussed with your advisor before the semester begins. **Due to covid-19, spring admissions have been opened up, therefore an additional offering of UN 5550 has been added to the Spring 2022 term. Note, students starting in Fall 2021 are highly encouraged to enroll in UN 5550 for the Fall semester - this course helps prepare you for other courses you may take. ***In Spring 2022, there are plans to also offer MA 5790. Note, the spring offering may not be available all years going forward.

Electives

At least 2 courses, 6 credits, must be taken from the list of approved elective courses in Table 1. Note, the options have changed over the years, be sure to select courses given the year you entered the program. ** Class offerings might change without notice. Please refer to the Registrar’s schedule of classes for actual class offerings.

Table 1. List of Elective Courses Academic Year student joined the program Course Course Offered

BA 5740 - Managing Innovation and Technology Fall X CS 5631 - Data Visualization Fall, Spring X X X CS 5841/EE 5841 - Machine Learning Spring X X X X CS 5471 - Computer Security Fall, Spring X X X X FW 5083 - Programming Skills for Bioinformatics Fall, alt. years X X X X MA 4710 - Regression Analysis Fall X X MA 5770 - Bayesian Statistics Fall, alt. years X X X MA 5781 - Time Series Analysis and Forecasting Spring X X X X MGT 4600 - Management of Technology and Innov. Fall, Spring X X X PH 4395 - Computer Simulation in Physics Spring X PSY 5210 - Advanced Stat. Analysis and Design I Fall, alt. years X X X X SAT 5114 - Introduction to AI and Health Fall X X X UN 5390 - Scientific Computing Fall, Spring X X X X

Foundational Courses

A maximum of six (6) credit hours of foundational skills course may be applied to the MS in Data Science. These courses will build skills necessary for successful completion of the MS in Data Science. Some students will not need to take these foundational courses and will instead use the domain electives to reach the credit requirements of this program. A list of foundational courses that can be taken towards the data science program is listed on the data science website and in Table 2.

Domain Elective Courses

Appendix A contains an extensive list of domain elective courses that can be taken towards the data science program. Your remaining credits of domain elective courses, 6-12 credits, can be taken towards the data science degree. Note : If there is a course not on the Domain Elective Course list, a student may petition the Graduate Program Director for its consideration. This petition must be submitted before the start of the semester for consideration.

To request a change of advisor or home department, please send an email, or meet with the graduate program director to initiate the process. The current advisor and the requested advisor should be contacted prior to initiating this process.

Registration / Scheduling

The graduate course catalog is located on the Registrar’s website. We recommend that your course schedule be determined in consultation with your advisor, data science director, or a member of the data science executive committee. It is important to set yourself up for success by ensuring that you have a suitable background to succeed in this interdisciplinary program. There are various foundational courses that can help strengthen your background in statistics, business or computing. All students should take UN5550, Introduction to Data Science, in the first semester of their studies. Information about registration can be found at the Registrar’s website. You may register online using the Banweb system or register in person at the Registrar’s Office, Room 130 of the Administration Building. Courses can be dropped or added through the first week of class without accruing any late penalty. If you have not paid for your courses by Wednesday of the first week of classes, your courses will be dropped.

Forms and Degree Completion Timelines

An important resource is the Graduate School’s Forms and Deadlines webpage. It is the student’s responsibility to complete forms and training courses in a timely fashion. Failure to meet submission deadlines could result in delayed completion of a student’s graduate degree. NOTE: graduate students must maintain a university cumulative GPA of 3.0 or above to be eligible for graduation.

Tuition Payment

After scheduling courses, go to MyMichiganTech to receive a copy of your schedule and tuition bill. You may pay your student bill online with American Express, MasterCard or Discover (2.3% transaction fee applies) or e-check, or at the Cashier’s Office located within the Student Financial Services Center in the Administration Building. Note: Credit/debit card payment not taken at Cashiers Office or by phone. For supported students only (GTA/GA/GRA): After scheduling courses, go to Banweb to view a copy of your schedule and tuition bill. Computer fees and tuition for up to 9 credits per semester will be paid by the program for fully supported students. You are responsible for the student voted fees such as the Student Activity Fee, and Experience Tech Fee, etc.

Continuous Enrollment

Students must be enrolled every academic-year (fall and spring) semester until they complete their degree. "Completing" a degree means successfully completing all required courses and turning in all required paperwork. Graduate students are not required to register for the summer session in order to fulfill the continuous enrollment policy. However, you can enroll in summer semester courses if you desire.

** International students are further required to maintain full-time status for fall and spring semesters, as a condition of their visa. Reduced course-loads are permissible only in certain circumstances. Please refer to documentation and forms required.

Career Placement

● Use the career center for help with interviews and resumes. In addition, you should plan on attending the Fall and Spring Career Fairs for finding internships and job leads. ● Students are strongly encouraged to create a Linkedin account and connect with the Michigan Tech Alumni Group. Social networking can be beneficial for expanding professional associations. ● Part-time on-campus employment opportunities for students may be available. The career center also maintains a list of local jobs aimed at Michigan Tech students: ○ www.career.mtu.edu/students/jobpostings.php ○ www.career.mtu.edu/students/jobresources.php

Internships / Co-ops

Internships and co-ops can provide valuable experience to your data science degree, in addition to expanding your network for future job prospects. To participate in a co-op, students must have a cumulative GPA of 3.0 or above, and adhere to deadlines posted. International students should contact IPS to ensure that requirements of their visas are fulfilled. ** Only internships and co-ops that are relevant to your data-science program may be counted towards the academic fulfillment of your data science degree. Students who wish to count co-op experience towards the academic fulfillment of the data science degree should provide the offer letter / job description to the program director for prior approval. If approved, up to three (3) credits of Co-op (UN 5000/ UN 5001 / UN 5002) can be counted towards academic fulfillment of the data science degree as a domain specialization elective.

Enterprise

In the Fall of 2018, we piloted several data science graduate enterprise projects. The enterprise project is intended to be a multi-semester learning experience, working on projects provided by industry. We are still trying to develop a path for data science graduate students to participate meaningfully in Enterprise. This will be updated as more information becomes available.

Re-using Credits

Students may double count up to 10 credits from one other Michigan Tech graduate program toward a Data Science masters degree, with the approval of the Data Science Program Director. Graduate credits earned toward the completion of a graduate degree at an institution other than Michigan Tech cannot be applied toward this degree program (this is a Michigan Tech policy).

Good Academic Standing and Dismissal

The Data Science Graduate Program follows the Graduate School policies on Good Academic Standing and Grading Policy.

Academic Grievances / Grade Appeals

Students wishing to appeal a grade assigned by a faculty member at Michigan Tech should follow the procedure described in the Michigan Tech Policy Statement under Academic Grievances.

Policies for Repeating Courses

For the data science degree, up to six (6) credits may be accepted with a B/C or C grade. Overall a 3. GPA must always be maintained, failure to do so will result in academic probation. Required courses can only be repeated once. If a student fails to earn a B or above in a required course after taking the required course twice, the student will be recommended for dismissal from the program. This policy applies even when the course is repeated at another institution.

Helpful Tips

Formatting Papers and Citing Research Material

All of your instructors expect you to properly cite and document sources of information in your work. Different instructors will prefer different formatting styles. Plagiarism is not tolerated and can result in dismissal from the graduate program. Be sure you are familiar with what constitutes a violation. When in doubt, please ASK your instructor or research advisor. A detailed booklet is available that describes Michigan Tech’s academic integrity policy and procedures.

Skills and Research Methodology

Although the Data Science Graduate Program is course-based, there will be numerous opportunities to work with professors on current research projects. Take the initiative to engage with faculty in your area of interest. Volunteer to assist with research tasks outside of class, above and beyond class assignments. Learn the methodology being used by the researcher. Be aware that:

● Statistics and quantitative skills are critical for data scientists. Not only should you be able to use a variety of statistical tools, but you also need to be able to understand the theoretical meaning and be adept at interpreting the results in productive and insightful ways. ● Core courses will require familiarity with a number of advanced computer skills. Invest time developing a solid understanding of a computer programming language such as Python, R and SAS. This will allow you to carry out more complex data analyses. ● Writing/communication skills are essential to a successful career. Michigan Tech provides assistance to improve your professional writing/communication. You should treat each and every writing/communication assignment as an opportunity to improve your communication skills.

Academic Integrity

Academic integrity and honesty are central components of a student's education, and ethical conduct fostered in an academic context will be carried into a student's professional career. Academic integrity is essential in a community of scholars searching and learning to search for truth. Anything less than total commitment to integrity undermines the efforts of the academic community. Both students and faculty are responsible for upholding the academic integrity of the University. For more information about policies related to Academic Integrity, please visit the Office of Academic and Community Conduct.

Computer Science CS 4425 Database Management System Design CS 4471 Computer Security CS 4811 Artificial Intelligence CS 5321 Advanced Algorithms CS 5331 Parallel Algorithms CS 5441 Distributed Systems CS 5496 GPU and Multicore Programming CS 5760 Human-Computer Interactions and Usability Testing CS 5811 Advanced Artificial Intelligence CS 5821 Computational Intelligence Electrical and Computer Engineering EE 5496 GPU and Multicore Programming EE 5500 Probability and Stochastic Processes EE 5521 Detection and Estimation Theory EE 5726 Wireless Sensor Networks EE 5821 Computational Intelligence Forest Resources and Environmental Science FW 5084 Data Presentation and Visualization with R FW 5411 Applied Regression Analysis FW 5412 Regression in R FW 5540 Remote Sensing of the Environment FW 5550 Geographic Information Science and Spatial Analysis FW 5555 Advanced GIS Concepts and Analysis FW 5556 GIS Project Management FW 5560 Digital Image Processing: A Remote Sensing Perspective Geological and Mining Engineering and Sciences GE 5150 Advanced Natural Hazards GE 5195 Volcano Seismology GE 5250 Advanced Computational Geosciences GE 5600 Advanced Reflection Seismology GE 5870 Geostatistics & Data Analysis

Mathematical Sciences MA 4330 Linear Algebra MA 4720 Design and Analysis of Experiments MA 5201 Combinatorial Algorithms MA 5221 Graph Theory MA 5627 Numerical Linear Algebra MA 5630 Numerical Optimization MA 5701 Statistical Methods MA 5741 Multivariate Statistical Methods MA 5750 Statistical Genetics MA 5761 Computational Statistics MA 5791 Categorical Data Analysis Mechanical Engineering - Engineering Mechanics MEEM 5010 Professional Engineering Communication Physics PH 4390 Computational Methods in Physics Social Sciences SS 5005 Introduction to Computational Social Science SS 5315 Population and Environment Applied Computing EET 4496 Applied Machine Learning SAT 5001 Introduction to Medical Informatics SAT 5141 Clinical Decision Support Modeling SAT 5151 Application Integration and Interoperability SAT 5241 Designing Security Systems SAT 5283 Information Governance and Risk Management SAT 5424 Population Health Management and Monitoring SAT 5761 Introduction to Hadoop and Applications SU 5010 Geospatial Concepts, Technologies, and Data Co-op UN 5000 Graduate Cooperative Education I