网红头条

Post Covid019, traffic congestion patterns have changed, specifically near elementary and middle school locations. More parents are choosing to use a personal vehicle as a primary mode of transportation to pick-up and drop-off their kids. In addition, parents of elementary and middle school kids who are part of the school choice program in Georgia must use the car to pick-up and drop-off their children. This process creates traffic congestion at intersections near schools during pick-up and drop-off times.

The goal of this project is to develop a safe and efficient transportation solution for GA parents of elementary and middle school children.

To achieve this goal, we will focus on two completing two objectives; (1) optimize traffic congestion at intersections near elementary and middle schools and (2) reduce total travel time for GA parents by developing a cloud-based application that integrates a smart-phone app with static vehicle detection sensors.

Each objective will be accomplished by (1) understanding current state-of-the-art (i.e. what are current solutions being offered for the same problem); (2) identifying various possible solutions (i.e. brainstorming possible solutions and listing pros and cons of each solution); (3) developing the best possible solution (i.e. collecting data, developing traffic simulation models, or developing cloud-based applications).

• Understand the research process.
• Learn how to conduct a literature review.
• Learn how to identify possible data collection sources online.
• Learn how to collect data in the field with data collection devices.
• Learn basics of traffic flow and traffic signal operations.
• Learn how to develop and calibrate traffic simulation models.
• Learn how to develop and test cloud-based applications.
• Learn how to develop surveys for data collection.

• Meet in-person or virtually.
• Learn relevant skills from the PhD student or an instructor.
• Perform specific tasks given at the end of the meeting.
• Update research team about the completed tasks. 

Hybrid

Dr. Parth Bhavsar, pbhavsar@kennesaw.edu

Steel Fiber Reinforced Concrete could be used to improve durability and toughness in concrete. Using steel fiber in production of concrete could eliminate the need for steel reinforcing. Cracking and fracturing under dynamic load could be prevented with enhancing the durability of concrete. Glass powder could improve the mechanical properties of concrete by the means of pozzolanic activity. Fly ash in concrete reduces cracking, permeability and bleeding creating high-durability concrete that is resistant to sulphates and alkali-aggregate reactions. The goal of this project is to produce high quality concrete mixture which could be resistant to dynamic loads, weathering with elimination the need for extra steel reinforcement with speeding the process of manufacturing precast elements. Steel fiber reinforced concrete has potential to reduce CO2, which is important for producing environmentally friendly concrete. This type of concrete could be widely used in infrastructure.

The selected first year student will be guided by Dr. Adrijana Savic in this research effort. This research can make use of students with interest in civil engineering.

At the end of the project, students should be able to:

1. Understand the materials needed to produce precast concrete.
2. Develop critical thinking skills for problems encountered in the lab 
3. Work effectively as part of a team
4. Present their research to an audience (e.g., poster, oral presentation, performance, display)

Typical activities for this research include:

1. Working in the lab to mix and cast steel fiber concrete beams. 
2. Test the concrete cylinders under failure
3. Collect data and compare the results: precast reinforcing concrete and steel fiber concrete.

Face-to-Face

Dr. Adrijana Savic, asavic@kennesaw.edu

Streamflow is an important quantity for hydraulics and water resources studies. Researchers and practitioners rely heavily on data from gaging stations to estimate streamflow for their work. Due to the sparse distribution of stream gages, there remain many ungaged streams and basins. Setting up and maintaining a vast network of stream gages is expensive and hence impractical.

This project will utilize an image processing technique, also known as the Large Scale Particle Image Velocimetry (LSPIV) for flow estimation. The LSPIV technique is capable of capturing surface velocity vectors and hence provide necessary information needed to estimate flowrates in strategic location along a stream. Motivated First-Year scholars will work in a team with graduate student(s) to accomplish for various tasks such as programming, laboratory work and field work to test the LSPIV system in the lab and in the field for flow estimation during various conditions. 

1. Understand and apply knowledge in electronics and programming 
2. student will be able to anticipate problems associated to fieldwork
3. Be able to collect data in the lab and from the field
4. Be able to articulate and present their research clearly

Participants to this project will be taught to think critically on what why the project is necessary and what the expected outcome is, through literature review.

Face-to-Face

Dr. Tien Yee, tyee@kennesaw.edu

Dr. Da Hu, dhu3@kennesaw.edu

 

While electric vehicles (EVs) are often considered emission-free, their increasing adoption can lead to higher air pollutant emissions from vehicles running on fossil fuels due to traffic congestion caused by the additional EV trips, as well as from power plants due to the increased energy demand from the grid. This project aims to leverage machine learning to develop a large-scale tool for estimating emissions from vehicles and power plants in response to rising EV adoption in major cities, including Atlanta, Los Angeles, New York, and Seattle. This integrated tool enables estimating the energy consumption of EVs from the power grid, as well as the emissions of CO2, NOx, and PM2.5 from traditional vehicles, and the increase in CO2, CH4, and N2O emissions from power plants due to the energy demand from EVs, with the projected increase in EV adoption over the coming years in the United States. 

• Enhance your expertise in machine learning and integrated modeling.
• Learn to use the EPA's MOtor Vehicle Emission Simulator (MOVES).
• Learn about the Cambium database developed by the National Renewable Energy Laboratory (NREL).
• Collaborate with graduate students on this research project.

• Biweekly meetings
• Complete the assigned tasks 

Hybrid

Dr. Mahyar Amirgholy, mamirgho@kennesaw.edu

A Software Defined Radio (SDR) is a radio transceiver that is primarily defined in software. It allows radio engineers and researchers to easily control the hardware and implement and configure the physical layer in software. SDRs have been used in many scientific platforms to implement, test, and study different wireless technologies and protocols. In this project, we explore the 5G waveform generation function of the MATLAB 5G Toolbox to generate different uplink-downlink transmission frames. 

The 5GNR (5G New Radio) 'knobs' include the bandwidth (BW), the physical resource block (PRB) allocation within the BW, the time slot occupation, the numerology, and the number of transmission layers, and the transmit (Tx) power. The generated waveform is transmitted over the air (OTA) using the GNU Radio software framework in conjunction with Universal Software Radio Peripheral (USRP) or other commercial SDR hardware. 

In the proposed work, two SDRs are used to implement the test bed's transmitter and receiver sides. Each SDR is connected by USB 3.0 to a GNU Radio Companion computer. The transmitter and the receiver GNU Radio flowgraphs have a built-in spectrum analyzer (SA) block to visualize the fast Fourier transform of the signal for spectral analysis. We use the 5G Toolbox because of its flexibility to customize the uplink and downlink 5G NR transmission that complies with the 3GPP specifications. In addition, we use another MATLAB function to convert the in-phase and quadrature (IQ) samples to binary points for use with GNU Radio. GNU Radio is a free and open-source software development toolkit that provides the mechanisms and sample signal processing blocks to implement radios in software. It is compatible with low-cost SDR hardware to enable RF transmission. 

Furthermore, it has a graphical user interface鈥擥NU Radio Companion鈥攖o assemble radios by connecting blocks. Moreover, we use a Software Defined Radio (SDR) and P21XXCSR-EVB Energy Harvesting module (existing) to conduct experiments on RF energy harvesting from the SDR transmissions. Specifically, we are interested in obtaining insight into joint communication and RF energy harvesting, aiming to transmit as much information as possible under the constraints of providing sufficient RF energy for the receiving device to operate. Experiments that will enable our insights into this problem include comparing communication waveform designs, comparing power emission via USRP, and the effect of environmental conditions like separation distance, presence of nearby in-band transmissions, and other factors.  

There are many high-impact situations where there is loss of telecommunication, for example natural disasters such as hurricanes and places where conventional telecommunication infrastructure is damaged such as in Ukraine, currently. In these cases, software definable, rapid deployable wireless communication systems are urgently needed. Our students will conduct high-impact research to solve crucial telecommunication problems, develop soft and entrepreneurial, and networking skills. We target external grants and industry support. We also prepare the students to use the analytical approach of an engineer, be able to integrate software, hardware and communication systems, and network infrastructures, and develop proof-of-concept projects related to future telecommunications. 

The students will develop essential articulation skills as we plan to present the work in seminars and other undergraduate symposiums.

Specifically, using the proposed test framework described above together with the related tutorials, the participant will be tasked with: 

• Understand the basics of modern communications using the provided tutorials and simulations
• Develop basic programming and testing of communications using the Matlab framework
• Perform test simulations using the 5G toolbox in Matlab to learn and utilize the various aspects of the toolbox.
• Familiarize with and utilize GNU Radio tools
• Generate a variety of 5G NR frames using the testbed (data generation in Matlab followed by transmission via GNU Radio).
• Manipulate the test parameters, including system bandwidth, waveform power, system gain, modulation, and subcarrier specifications. Analyze the results
• Compare the testbed performance to simulation results.
• Measure the energy harvested via signal transmission.
• Innovate and Implement strategies to improve energy harvesting while maintaining transmission rates

Face-to-Face

Dr. Sumit Chakravarty, schakra2@kennesaw.edu

The primary goal of this project is to apply a novel light-based sensor (like how an Apple Watch monitors heart rate using green light) for noninvasive measurements of muscle health and function in older adults. Age-related reductions in muscle strength and function, known as 鈥渟arcopenia,鈥� significantly impact mobility, quality of life, and mortality in older people. Noninvasive assessment of muscle function during exercise would be immensely valuable for the early diagnosis of sarcopenia and for monitoring the effectiveness of therapeutic interventions. Unfortunately, current technologies are insufficient for assessing oxygen delivery and utilization at the microvascular level during exercise, and existing laboratory methods are limited.

Our light-based sensor directly measures muscle blood flow and oxygenation. During daily activities, the energy required for muscle function primarily comes from oxygen metabolism. Adequate oxygen delivery to muscles through normal blood flow is critical to meeting the metabolic demands during daily activities and exercise. This light-based technique allows for continuous, noninvasive monitoring of oxygen delivery and consumption in muscles during exercise. For  this project, we will place our sensors on one of the thigh muscles while human subjects perform knee extension exercise. We will recruit  young and  older adults to determine if there are differences in oxygen delivery and consumption between the two age groups.

Throughout this project, the undergraduate student will engage in state-of-the-art biomedical research by applying novel medical devices to human subjects. The student will have the opportunity to receive mentoring from an interdisciplinary advisory group from the College of Engineering and Wellstar College of Health and Human Services. The student will gain a diverse range of skills, including basic engineering, biophotonics, muscle physiology, data acquisition and analysis in human subjects, and scientific communication, including symposium abstract writing and presentation skills.

• Gain essential knowledge on biomedical optics 
  
• Understand a principle of light-based sensors (Like Apple Watch) 
  
• Experience in interdisciplinary research covering engineering and health
  
• Experience in research directly involving human subjects 
  
• Relevant training for ethics, safety and compliance
  
• Collecting data on human subjects
  
• Perform optical spectroscopic sensing and data analysis 
  
• Enhance professional communication skills

Literature review in biomedical optics and applications in noninvasive muscle function monitoring 
鈥� Learn how to operate optical devices 
鈥� Assist with human data collection 
鈥� Data analysis on the acquired optical data
鈥� Present research progress in a weekly lab group meeting
鈥� Prepare presentations for conferences.  

Hybrid

Dr. Paul Lee, slee274@kennesaw.edu

Dr. Garrett Hester, ghester4@kennesaw.edu

Dr. Daphney Carter, dcart165@kennesaw.edu

Neuromorphic electronics and neuromorphic computer chips can enable superior artificial intelligence. Developing such computer chips involve designing and fabricating artificial synapses 鈥� a key component for the transmission of electrical signals mimicking signal transmission within the human brain. In this project we focus on the development of Memristor-based artificial synapses. 

A 'memristor' is a type of fundamental electronic device that has the feature of a memory and a resistor in one element. Such unique properties make memristors useful for building electronic circuits that mimic the synaptic connections in biological neural networks, enabling the development of artificial neurons and neural networks for futuristic neuromorphic computers that can process information like the human brain. Such neuromorphic computers find applications in Artificial Intelligence, Machine Learning, and brain-inspired computing systems. In addition, memristors can be used in many emerging technologies, such as non-volatile memories (ReRAM), Analog Signal Processing units, In-Memory Computing, Data Encryption, Hardware Security, Reconfigurable Logic Circuits, Smart Sensors, and Cognitive Computing systems that can adapt and learn from the environment, making them useful in intelligent robotics and autonomous systems.

This FYSP project focuses on the research and development of memristor devices that are the basic building blocks for artificial synapses and neuromorphic computing chips. The specific aim of this project is to 鈥� design and fabricate a memristor system and test its performance/ characteristics in the laboratory. By the end of the project, we aim to demonstrate a working device/system that is capable of generating a pinched current-voltage hysteresis signature exhibited by memristors. The overarching goal is to develop low-cost memristor technology to accelerate the research, development, and education in the emerging field of neuromorphic computer chips. The first-year research scholars will learn how electronic devices and circuits can be designed and fabricated that can mimic the synapses of a human brain. They will gain invaluable knowledge and experience on memristor devices and learn how to fabricate an artificial synaptic device. Participating student researchers will receive hands-on training in electrical measurements and testing of devices and circuits, design and simulate circuits, learn to build complex circuits on a breadboard and/or PCB, and develop many important and useful engineering research skills through this project. We are looking forward to forming a multidisciplinary team with students from Electrical Engineering, Computer Engineering, Mechatronics Engineering, Computer Science, Information Technology, and Physics majors to work on this project.

1. Learn how to perform literature research and formulate creative solutions.
2. Build memristor device/circuits.
3. Learn electronic test and measurement techniques.
4. Learn how to operate various lab instruments.
5. Design Experiments and implement test routines by embedded programming.
6. Apply PCB design and PCB fabrication techniques.
7. Implement data plot and data analysis techniques.
8. Develop teamwork, presentation, and communication skills.

• Study research articles to learn how the human brain functions and how electronic artificial synaptic devices can be used to mimic some of the brain鈥檚 functions.
• Learn how memristors can be used as an artificial synaptic device and to create an artificial neuron or neural network.
• Design and simulate circuits to realize an electronic memristor-type device.
• Fabricate a memristor device/circuit and test its performance.
• Perform experiments, acquire data using lab instruments, and analyze experimental data. 
• Attend weekly research group meetings and update the PI.
• Document the research results, make presentations and write reports.

Hybrid

Dr. Sandip Das, sdas2@kennesaw.edu

Neuro-symbolic AI (NSAI) represents an emerging AI paradigm that integrates neural, symbolic, and probabilistic approaches to enhance explainability, robustness, and enable learning from much less data in AI. Neural methods have proven highly effective in extracting complex features from data for tasks such as natural language processing and object detection. On the other hand, symbolic methods enhance explainability and reduce the dependence on extensive training data by incorporating established models of the physical world, and probabilistic methods enable cognitive systems to handle uncertainty more effectively, resulting in improved robustness under unstructured conditions. The synergistic fusion of neural, symbolic, and probabilistic methods positions NSAI as a promising paradigm capable of ushering in the third wave of AI. NSAI holds significant potential for enhancing real-time responses, energy efficiency, explainability, and trustworthiness of collaborative human-AI applications. 

In this project, we will address the challenges of robotic learning and planning, which are complicated by continuous state spaces, continuous action spaces, and long task horizons. We will explore a bi-level planning scheme where symbolic AI planning in an outer loop guides continuous planning with neural models in an inner loop. Eventually, we expect to merge the model with the vector symbolic architecture and make it run smoothly on edge devices like microcontrollers or single-board computers for energy efficiency.

In the proposed project, our first-year scholar will collaborate with other research lab members and learn basic concepts in neural symbolic AI. More importantly, the scholar will enjoy the opportunity to play with various robots, such as life-size robot dogs and small humanoids, for demonstrations. 

•  Gain essential knowledge in neural-symbolic AI.
• Explore the algorithm design under the hardware constraints and tradeoffs
• Collaborate with other undergraduate and graduate students in our teams
• Gain research skills systematically and understand the research process.
• Acquire abilities in academic writing, presentation, and communication.
• Improve skills in solving practical engineering problems.

• Weekly meeting and report the progress.
• Discuss the project with the advisor and collaborators.
• Study algorithms and explore the implementation on hardware.
• Evaluate the system performance.
• Accomplish a final report and complete a research poster presentation. 

Hybrid

Dr. Yan Fang, yfang9@kennesaw.edu

Fused deposition modeling (FDM) is one of the additive manufacturing processes gaining ground in today's industry. FDM or material extrusion (MEX) printing can create parts with 鈥渋nfill鈥� which refers to the amount of material inside the part, and 鈥渞aster angle", which refers to the amount of material inside the part. FDM creates parts in which the properties depend on the direction which the parts are made.

Because of the layer-by-layer process of manufacturing parts, different properties can occur depending on the direction of manufacture, often called anisotropy. Despite its advantages, the inability to predict failure and the variability of the mechanical properties of parts manufactured through this process is still difficult. This research aims to study the influence of these parameters on additively manufactured specimens subjected to tensile and impact loads and better understand the anisotropic nature. To advance the understanding of this anisotropic nature, tensile and impact specimens will be manufactured using material extrusion and tested according to ASTM standards.

In addition to physical testing, computer-aided models will be refined as needed to reflect the 鈥渞eal world鈥� behavior better to understand the anisotropic nature. The computer-aided models
and physical tests will be compared to verify the accuracy of simulations in predicting failure. The results of the research will aid engineers in the analysis of parts prior to manufacture.

Students will develop research and testing techniques through real-world and novel testing. These skills will be invaluable to young researchers who want to contribute and impact through modern additive manufacturing.

Furthermore, the skills acquired through this program will be helpful for someone wanting to become a researcher or attend graduate school.

Students will perform scholarly research and perform physical testing.

Students will also be responsible for meaningful contributions, as well as weekly meetings and deadlines.

Face-to-Face

Dr. Aaron Adams, aadam224@kennesaw.edu

Dr. David Stollberg, dstollbe@kennesaw.edu

Dr. Cameron Coates, ccoates4@kennesaw.edu

Abstract:
Blood transfusion is a crucial service of health care systems and contributes to saving and improving millions of lives every year [1], given the increasing complexity of medical and surgical interventions, and improves both life expectancy and quality of life of blood recipients. Since the manufacture of blood in the laboratory is currently impossible, continual blood donor recruitment is critical due to declining blood donations from donors, which threatens national supplies in many countries, including the United States [2] [3]. Various types of emerging technologies, such as mHealth apps [4], virtual reality [5], and blockchain technology [6] to name a few, are being employed in the blood donation industry to attract new donors, process blood products, or deliver blood products to healthcare partners. Artificial intelligence (AI) is an emerging technology that is gaining widespread attention in virtually every industry today, including the blood donation industry [7]. In this research, we explore both current and potential uses of emerging technologies in the procurement, processing, and distribution of blood products to meet the nations鈥� daily blood supply needs.

References:
1. Fordham J, Dhingra N. Towards 100% voluntary blood donation. A global framework for action. World Health Organization, Geneva, 2010.
2. Simon T. Where have all the blood donors gone? A personal reflection on the crisis in America鈥檚 volunteer blood program. Transfusion. 2003: 43(2):273-279. https://doi.org/10.1046/j.1537-2995.2003.00325.x.
3. Sullivan M, Cotton, R, Read E, Wallace, E. Blood collection and transfusion in the United States in 2001. Transfusion. 2007;47(3):385-394. DOI: https://doi.org/10.1046/j.1537-2995.2003.00325.x. PMID: 12559025.
4. Li L, Valero M, Keyser R, Ukuku A, Zheng D. Mobile applications for encouraging blood donation: A systematic review and case study. Digital Health. 2023;9:1-15. https://doi.org/10.1177/20552076231203603. PMID: 37822963. PMCID: PMC10563464.
5. Abbott Laboratories. Taking blood donation to a new dimension of reality. 2023. https://www.abbott.com/corpnewsroom/diagnostics-testing/taking-blood-donation-to-a-new-dimension-of-reality.html.
6. Varghese A, Thilak K, Thomas S. Technological advancements, digital transformation, and future trends in blood transfusion services. Int J Adv Med. 2024;11(2):147-152. https://doi.org/10.18203/2349-3933.ijam20240368
7. Raturi M, Dhiman Y, Khatiwada B, Gaur D, Adhikari B, Rawat P. The role of artificial intelligence in optimizing the donation process and predicting blood thresholds. Transfus Clin Biol. 2023;30(4):458-459. https://doi.org/10.1016/j.tracli.2023.08.004. PMID: 37597607.

1. Students will learn how to effectively conduct a Literature Review.
2. Students will improve their teamwork, time management, writing, and oral presentation skills.
3. Students will build responsibility, commitment, and accountability in meeting deadlines with high-quality work.

1. We will spend several weeks conducting a Literature Review and categorizing manuscripts by common themes.
2. We will spend several weeks on a journal manuscript prep.
3. Students will prepare a poster or oral presentation for the 2025 IISE Healthcare Systems Process Improvement Conference in Feb 2025.
4. Students will prepare a poster or oral presentation for the SP25 KSU Symposium of Student Scholars in April 2025.

Online

Dr. Robert Keyser, rkeyser@kennesaw.edu

Dr. Lin Li, lli19@kennesaw.edu

Blood transfusion is a crucial service of health care systems and contributes to saving and improving millions of lives every year [1], given the increasing complexity of medical and surgical interventions, and improves both life expectancy and quality of life of blood recipients. Since the manufacture of blood in the laboratory is currently impossible, continual blood donor recruitment is critical due to declining blood donations from donors, which threatens national supplies in many countries, including the United States [2] [3]. In this research, we will administer a blood donation survey specifically targeting the Latinx community, an underrepresented population in the blood donation process. We intend to administer the survey via the Georgia Dept. of Public Health and the KSU student organization, HOLA. The FYSP student will obtain CITI certification in Human Subjects research, be added to our IRB application, assist with data analysis, manuscript prep, posters, and presentations at the KSU Symposium of Student Scholars (FA24 or SP25) and the Healthcare Systems Process Improvement (HSPI) conference in Atlanta in Feb 2025.

References:
1. Fordham J, Dhingra N. Towards 100% voluntary blood donation. A global framework for action. World Health Organization, Geneva, 2010.
2. Simon T. Where have all the blood donors gone? A personal reflection on the crisis in America鈥檚 volunteer blood program. Transfusion. 2003: 43(2):273-279. https://doi.org/10.1046/j.1537-2995.2003.00325.x.
3. Sullivan M, Cotton, R, Read E, Wallace, E. Blood collection and transfusion in the United States in 2001. Transfusion. 2007;47(3):385-394. DOI: https://doi.org/10.1046/j.1537-2995.2003.00325.x. PMID: 12559025.

1. Describe past research studies in their field of study 
2. Evaluate research studies they see in the media or encounter in literature 
3. Write papers and research reports 
4. Develop problem-solving skills 
5. Present their research activity to an audience. 

1. Find papers related to the problem 
2. Summarize papers 
3. Find gaps in the research 
4. Discuss research directions with faculty mentors.
5. Meet weekly with faculty mentors.
6. Write research papers 

Hybrid

Dr. Lin Li, lli19@kennesaw.edu

Dr. Robert Keyser, rkeyser@kennesaw.edu

In this research project, students will engage in advanced nanoscale computational modeling to investigate the thermal transport properties of novel low-dimensional nanomaterials, specifically graphene and hexagonal boron nitride (h-BN). This research, part of a newly funded NSF project, aims to advance our understanding of these cutting-edge materials. Students will delve into the mechanical behavior of nanomaterials, exploring their response under various conditions at the nanoscale, and gain hands-on experience with molecular dynamics simulations, learning how to set up, run, and interpret results from complex computational models.

As part of the research process, students will document their findings and methodologies thoroughly, improving their technical writing skills and preparing detailed technical reports. Participating in this project will allow students to stay abreast of the latest developments in the field of nanomaterials, work with state-of-the-art computational tools and techniques, and gain insights directly applicable to both academic and industry settings. The skills and knowledge acquired through this research are highly valuable and transferable, providing significant assets whether students choose to pursue further academic research or enter the industry. Additionally, students will work closely with faculty members and other researchers, fostering a collaborative environment that encourages the exchange of ideas and peer learning, thus enhancing their research experience and building a network of professional relationships that can benefit their future careers.

In summary, this research project offers a comprehensive learning experience that combines theoretical knowledge with practical application, equipping students with a deeper understanding of nanomaterials, advanced computational skills, and enhanced technical writing abilities crucial for their professional development in the field of engineering and materials science.

While working on this project, students will develop a range of valuable skills and techniques essential for academic research and professional development in engineering and materials science. They will gain hands-on experience with computational modeling, particularly molecular dynamics simulations, to study the thermal transport properties of nanomaterials like graphene and hexagonal boron nitride. Students will deepen their understanding of nanomaterial mechanics, use advanced simulation software, and improve their technical writing by documenting findings in detailed reports. They will enhance their data analysis and problem-solving abilities, collaborate closely with faculty and peers, and learn effective time management. Critical thinking will be fostered as they analyze results and question assumptions, while presentation skills will be honed through opportunities to present their research. This comprehensive skill set will prepare students for successful careers in scientific research and beyond.

Each week, students will engage in various activities designed to build their skills and advance the research project. They will set up and run molecular dynamics simulations, analyze the resulting data, and read recent scientific papers to stay informed about the latest developments in the field. Weekly group meetings with faculty advisors and peers will provide a forum for discussing progress, sharing challenges, and receiving feedback, while technical writing tasks will help students document their research process and results in detailed reports. Periodic workshops will teach specific skills such as advanced data analysis techniques and effective use of simulation software. Students may also conduct complementary experimental activities to validate their computational models, participate in problem-solving sessions to address specific research challenges, and collaborate with peers on joint tasks. Towards the end of each week, students will prepare and deliver presentations summarizing their progress and plans for the upcoming week, ensuring continuous feedback and enhancing their communication skills. These structured activities provide a balanced and comprehensive research experience, equipping students with the necessary skills and knowledge to succeed in their academic and professional endeavors.

Face-to-Face

Dr. Jungkyu Park, jpark186@kennesaw.edu

This project aims to develop a cutting-edge digital twin of the human heart through advanced machine learning techniques. A digital twin is a virtual model of a physical entity鈥攊n this case, the human heart鈥攖hat can simulate its behavior in real-time using patient-specific data. Our research integrates diverse data sources, including ECG (electrocardiogram), pressure measurements, and 4D CT imaging, to create highly accurate and personalized models of heart function.

The project will engage first-year students in a comprehensive research experience, where they will contribute to various aspects of this innovative study. Students will work on tasks such as data preprocessing, machine learning model development, and simulation validation. By participating, students will gain hands-on experience with cutting-edge technologies and learn how to apply machine learning to solve complex biomedical problems.

Throughout the year, students will be involved in:

1. Data Analysis: Handling and analyzing real patient data, including ECG signals, pressure readings, and 4D CT images. Students will learn how to preprocess and prepare these datasets for modeling.

2. Model Development: Building and training machine learning models to simulate heart mechanics. Students will work with advanced algorithms and learn how to optimize models for accuracy.

3. Simulation and Validation: Running simulations to compare model predictions with actual patient data. Students will assess the performance of the digital twin and make necessary adjustments.

4. Presentation and Reporting: Preparing and presenting their findings at the Symposium of Student Scholars in April. Students will also be responsible for documenting their progress and contributing to mid-year and end-of-semester evaluations.

Mentorship will include regular meetings to guide students through their research tasks and ensure they meet project milestones. Students will also participate in mandatory orientation sessions and complete required progress reports. This project provides a unique opportunity for first-year scholars to delve into interdisciplinary research, bridging machine learning and biomedical sciences, while developing essential research skills and contributing to the advancement of personalized medicine.

In working on the project "Creating a Digital Twin of the Human Heart Using Machine Learning," students will gain valuable skills and techniques essential for both research and professional development. Key skills include:

1. Data Analysis and Preprocessing: Students will learn to handle and preprocess complex datasets, including ECG signals, pressure measurements, and 4D CT images. They will acquire skills in data cleaning, normalization, and transformation to prepare data for analysis.

2. Machine Learning Techniques: Students will gain experience in applying machine learning algorithms to develop predictive models. They will learn about various techniques, including supervised learning, neural networks, and deep learning. Practical experience with model training, validation, and optimization will be key components.

3. Programming and Software Tools: Proficiency in programming languages such as Python will be developed, along with familiarity with libraries and frameworks like TensorFlow, PyTorch, and scikit-learn. Students will also gain experience with data visualization tools and software for model implementation.

4. Simulation and Modeling: Students will learn to create and validate simulations of heart mechanics using digital twin technology. They will understand how to integrate real patient data into these models and assess their performance against actual outcomes.

5. Critical Thinking and Problem-Solving: The project will enhance students' problem-solving skills by challenging them to address complex research questions and optimize their models based on performance metrics and data analysis.

6. Communication and Presentation: Students will develop skills in communicating complex research findings effectively. They will prepare and present their results at the Symposium of Student Scholars, learning how to articulate their research processes and outcomes to diverse audiences.

Students will engage in a variety of activities each week as part of the project "Creating a Digital Twin of the Human Heart Using Machine Learning." These activities will include:

1. Data Segmentation and Processing: Weekly, students will work on segmenting 3D models from CT data. This involves using specialized software to extract relevant structures and features from the imaging data. They will also preprocess and prepare these models for further analysis.

2. Machine Learning Techniques: Students will dedicate time each week to learning and applying machine learning techniques. This includes studying various algorithms, such as neural networks and deep learning models, and understanding their applications in simulating heart mechanics. They will implement these techniques using programming languages and tools like Python and PyTorch.

3. Algorithm Training and Simulation: Students will apply machine learning algorithms to train models with the prepared data. This involves running simulations, adjusting model parameters, and refining their approaches based on performance metrics. They will work on developing and validating accurate simulations of heart function.

4. Bi-Weekly Meetings: Every two weeks, students will meet with me to discuss their progress, present their results, and receive feedback. These meetings will provide an opportunity to address challenges, refine techniques, and ensure alignment with research objectives.

5. Presentation Preparation: At the end of each semester, students will prepare a presentation to showcase their work and outcomes. This includes summarizing their research activities, data analysis, and results. They will practice presenting their findings clearly and effectively to both peers and faculty. 

Hybrid

Dr. Lei Shi, lshi@kennesaw.edu

The project focuses on investigating the aerodynamic behavior of tandem wing configurations, a topic of significant importance in the design of advanced aircraft and unmanned aerial vehicles (UAVs). The primary objective is to understand the complex interactions between the vortices generated by the leading wing and their impact on the aerodynamic performance of the trailing wing. This research is driven by the need to optimize tandem wing arrangements, which can potentially offer higher lift-to-drag ratios, improved stability, and enhanced maneuverability in various flight regimes.

The study will employ advanced computational fluid dynamics (CFD) techniques to simulate the flow fields around the tandem wing configuration. The numerical analysis will be conducted using high-fidelity CFD software, with turbulence modeling approaches such as Reynolds-Averaged Navier-Stokes (RANS), Large Eddy Simulation (LES), or Detached Eddy Simulation (DES) to capture the intricate details of vortex formation, shedding, and interaction. The simulation results will provide detailed insights into the wake dynamics, vortex trajectories, and their influence on the pressure distribution, lift, drag, and overall aerodynamic efficiency of the tandem wing arrangement.

A key aspect of the project is the parametric study, where different wing configurations, spacing, and angles of attack will be analyzed to determine their effect on vortex interaction and aerodynamic performance. The study will also explore the effects of varying Reynolds numbers to understand the performance characteristics across different flight conditions. The results from the numerical simulations will be validated against available experimental data or empirical correlations to ensure accuracy and reliability.

The outcomes of this research are expected to contribute to the design guidelines for tandem-wing aircraft, enabling the development of more efficient and high-performance aerial vehicles. The findings will have implications for both military and civilian applications, where tandem wing configurations are being considered for their potential advantages in specific mission profiles.

Overall, this project aims to advance the understanding of vortex interactions in tandem wing arrangements, providing valuable insights that can lead to innovative design strategies in the aerospace industry. The research will culminate in the development of comprehensive design recommendations and potential optimization strategies for future tandem-wing aircraft designs.

Students participating in this project will develop a robust set of skills and techniques that are essential for careers in aerospace engineering and related fields.

Firstly, students will gain hands-on experience with advanced computational fluid dynamics (CFD) software, learning how to set up, run, and analyze simulations of complex aerodynamic systems. They will become proficient in using CFD tools such as ANSYS Fluent, which are industry standards, and will learn how to apply different turbulence modeling approaches like Reynolds-Average Navier-Stokes Equations (RANS), Large Eddy Simulation (LES), or Detached Eddy Simulation (DES) to capture the intricate details of vortex dynamics.

In addition to technical software skills, students will develop strong analytical and problem-solving abilities. They will learn to interpret the complex data generated from simulations, extracting meaningful insights into the behavior of vortices in tandem wing configurations. This process will involve understanding and applying fundamental aerodynamic principles, as well as critically evaluating the accuracy and reliability of their results.

Moreover, students will enhance their research and experimental design skills by conducting a parametric study to explore the effects of different wing configurations, spacing, and angles of attack. They will learn how to design experiments that test specific hypotheses, control variables effectively, and draw conclusions based on empirical data.

Collaboration and communication skills will also be a significant focus. Students will work in teams, learning how to collaborate effectively, share responsibilities, and integrate their contributions into a cohesive research effort. They will also develop the ability to communicate their findings clearly and concisely, whether through written reports, presentations, or discussions, which is critical for any professional or academic career.

Overall, this project provides students with a comprehensive skill set that prepares them for future challenges in both academic and industry settings.

Throughout the two-semester duration of this project, students will engage in a series of structured and progressive activities designed to build their skills, knowledge, and research capabilities. The proposed tentative plan for two semesters is as follows:

Semester 1:

Weeks 1-3: Orientation and Background Research

• Students will start by reviewing fundamental concepts in aerodynamics and computational fluid dynamics (CFD).
• They will engage in literature reviews to understand current research on tandem wing configurations and vortex interactions.

Weeks 4-6: CFD Software Training

• Hands-on training sessions with CFD software (e.g., ANSYS Fluent) will be conducted.
• Students will complete basic tutorials to become familiar with setting up simulations, mesh generation, and running simple flow analyses.

Weeks 7-10: Simulation Setup and Preliminary Runs

• Students will begin setting up initial simulations of a basic tandem wing configuration.
• They will define the geometry, select appropriate turbulence models, and perform preliminary simulation runs.

Weeks 11-15: Data Analysis and Mid-Semester Review

• Students will analyze the initial simulation data, focusing on vortex formation and flow characteristics.
• A mid-semester review will be conducted, where students present their findings and receive feedback to guide the next phase of the project.

Semester 2:

Weeks 1-4: Advanced Simulation Runs

• Students will refine their simulation models based on feedback and extend their analysis to more complex wing configurations.
• They will conduct a parametric study to explore the effects of varying spacing, angles of attack, and Reynolds numbers.

Weeks 5-8: Validation and Comparison

• Students will validate their simulation results against existing experimental data or empirical correlations.
• They will perform comparative analyses to evaluate the accuracy and reliability of their models.

Weeks 9-12: Documentation and Presentation Preparation

• Students will compile their findings into a comprehensive report.
• They will develop presentations for internal reviews, conferences, or potential publications.

Weeks 13-15: Final Review and Reflection

• A final project review will be held, where students present their complete research findings.
• They will reflect on the research process, discussing lessons learned and potential future research directions.

Hybrid

Dr. Gaurav Sharma, gsharma3@kennesaw.edu

This research aims to advance artificial intelligence (AI) for detecting bruises and assessing the quality of fruits using cameras at manufacturing sites. By improving AI techniques, we can enhance fruit quality and extend shelf life. The study employs convolutional neural networks (CNNs), semantic segmentation, and object detection.

The research will begin with annotating images of bruised fruits using bounding boxes to create a comprehensive dataset. We then apply preprocessing techniques and data augmentation to optimize the dataset for training AI models. Common challenges include variations in lighting across different cameras and different fruit orientations. AI models will be developed to accurately identify bruised areas on fruit surfaces. We will use various segmentation techniques for locating bruised regions and semantic segmentation for higher accuracy. Object detection will further assess and classify defects by measuring the size and severity of bruises. These AI models will be integrated into fruit sorting automation systems. High-speed fruit production often relies on automated sorting to handle large volumes, as manual sorting is insufficient and can cause additional damage. AI techniques will address practical issues such as varying illumination and inconsistent fruit orientations during sorting, reducing fruit loss and improving efficiency. The models' performance will be evaluated using industry-standard metrics to ensure accuracy, reliability, and effectiveness in real-world settings. 

Overall, this research seeks to bridge the gap between advanced AI techniques and practical applications in agriculture. By developing a lightweight, AI-driven fruit quality assessment system, the study aims to improve fruit sorting and quality control practices, particularly by efficiently identifying and grouping bruised fruits for lower-priced sales.

The students' learning outcomes from the project on leveraging AI for fruit quality control could include:

1. Application of AI Techniques: Students will be able to apply advanced AI techniques such as convolutional neural networks, semantic segmentation, and object detection to solve real-world problems in agriculture.

2. Data Collection and Preprocessing: Students will learn to collect and preprocess high-resolution images of fruits, ensuring consistency in lighting and orientation, which are crucial for training effective AI models.

3. Model Development and Evaluation: Students will develop AI models capable of identifying and measuring bruises on fruits. They will also evaluate these models using industry-relevant metrics to ensure accuracy and reliability in practical settings.

4. Problem-Solving Skills: Through the project, students will enhance their problem-solving skills by addressing challenges such as varying lighting conditions and fruit orientations in the application of AI.

5. Integration of AI in Industry: Students will understand how to integrate AI models into automated systems, improving efficiency and accuracy in fruit sorting processes, which is crucial for high-speed operations in the industry.

6. Research and Development: Students will contribute to bridging the gap between theoretical AI techniques and practical agricultural applications, gaining insights into research and development processes.

Students will be working on these phases:

Introduction and Overview

- Orientation session introducing the project objectives, importance of fruit quality control, and the role of AI.

Data Collection

- Collect high-resolution images of various fruits with different levels of bruising.

Data Annotation

- Annotate the collected images to mark bruised areas and categorize defects.

Preprocessing Techniques

- Learn and apply preprocessing techniques to optimize images for model training (e.g., adjusting lighting and orientation).

Model Selection and Training

- Introduction to various AI models (CNNs, semantic segmentation) and begin training selected models on the dataset.

Model Evaluation

- Evaluate the trained models using industry-relevant metrics (accuracy, reliability).

Integration into Automated Systems

- Explore how the developed models can be integrated into automated fruit sorting systems.

Addressing Real-World Challenges

- Discuss and devise strategies to tackle challenges such as varying lighting conditions and fruit orientations.

Continuous Improvement and Feedback Loop

- Analyze how ongoing use of AI can improve model accuracy and performance over time.

Final Presentation and Reporting

- Prepare a presentation summarizing findings, model performance, and potential impacts on the fruit industry.

Face-to-Face

Dr. Sathish Kumar Gurupatham, sgurupat@kennesaw.edu

Welcome to the future of Artificial General Intelligence (AGI)! Our project, AGI CORE, focuses on the exciting and groundbreaking field of AGI, particularly its application in real-time control of ecosystems involving robotics and various environments. Imagine a world where machines can understand, learn, and adapt just like humans, creating seamless interactions between intelligent machines like robots, their surroundings, and humans.

AGI is in its inception phases, making this an incredibly exciting time to get involved. Our project aims to develop intelligent systems capable of real-time decision-making and autonomous control. These systems will be able to manage complex environments, such as smart homes, autonomous vehicles, robotic assistants, and biomedical applications. Picture a smart healthcare system where AGI can analyze patient data, monitor vital signs with embedded sensors, and assist in surgeries with robotic precision.

Joining AGI CORE in the VOICU (Vision of Immortal Cell Understanding) lab will put you at the forefront of this emerging discipline. We have access to cutting-edge robotic systems, sensors, and embedded units, providing you with the tools to explore and innovate. We seek enthusiastic students eager to grow and learn during and beyond the first-year program. This project offers a unique opportunity to work on cutting-edge technology, develop technical and soft skills, and contribute to significant advancements in AGI. You will hone your programming abilities, work with advanced AI algorithms, and gain experience with real-time systems. Additionally, you will enhance your problem-solving, teamwork, and communication skills, essential for professional growth.

Whether you're passionate about robotics, artificial intelligence, biomedical applications, or innovative problem-solving, AGI CORE provides a platform to explore and expand your horizons. We invite students from all disciplines to join us, as there is room for growth for those in the sciences, including biology, chemistry, physics, humanities, arts, and beyond. Imagine an AGI system developing new music or art. AGI, with its human-like intelligence, seeks to understand and interact with the world in a way that integrates knowledge from diverse fields, making your unique perspective invaluable.

You'll collaborate with a diverse team of students and faculty, gaining hands-on experience and developing skills that will set you apart in the rapidly evolving tech landscape. Join us in shaping the future of intelligent systems and making a meaningful impact on the world. Together, we'll push the boundaries of what AGI can achieve and pave the way for a smarter, more connected future.

Participating in the AGI CORE project will equip students with a diverse set of skills and techniques, preparing them for future careers in AI, robotics, and other related fields. Here are some of the key outcomes:

Technical Skills: Students will gain proficiency in programming languages such as Python and C++, which are essential for developing AGI systems. They will learn to implement machine learning algorithms, work with neural networks, manage large datasets, and understand the fundamentals of artificial intelligence. Additionally, they will explore and understand multimodal AGI, integrating various forms of data such as visual, auditory, and textual inputs to create more robust intelligent systems.

Hands-on Experience: Through practical projects, students will design, build, and test intelligent systems. They will work with advanced robotics platforms, sensors, and embedded units, gaining experience in hardware integration and real-time system control.

Research Skills: Students will develop strong research abilities, including literature review, hypothesis formulation, experimental design, and data analysis. They will document their findings and prepare research papers for publication, contributing to the academic community.

Soft Skills: The project emphasizes developing soft skills such as problem-solving, teamwork, and communication. Students will collaborate with peers and mentors, enhancing their ability to work effectively in diverse teams and present their ideas clearly.

Interdisciplinary Knowledge: Students will learn to approach problems from multiple perspectives by integrating knowledge from various fields. This holistic understanding is crucial for developing innovative AGI solutions that interact seamlessly with human environments.

Professional Growth: The experience gained through AGI CORE will make students attractive candidates for internships, jobs, and further academic pursuits. They will build a portfolio of work demonstrating their capabilities and accomplishments.

By the end of the project, students will have a comprehensive skill set and practical experience, positioning them for success in the rapidly evolving tech landscape.

Students involved in the AGI CORE project will engage in various weekly activities, ensuring a well-rounded and immersive learning experience. Here's a breakdown of potential weekly duties:

Programming and Development: Students will dedicate time to coding and developing algorithms for AGI systems, including developing AI Assistants. This includes writing and testing code, debugging, and optimizing performance to ensure efficient operation of intelligent systems.

Research and Literature Review: Students will review scholarly articles and research papers to stay updated with the latest advancements in AGI, helping them to understand current trends, identify gaps in the field, and generate new ideas for their projects.

Experimentation: Students will conduct experiments to test their AGI models. This involves setting up experiments, collecting data, and analyzing results to evaluate the effectiveness of their solutions. They will iterate on their designs based on the findings.

Team Meetings: Regular meetings will be held to discuss progress, share insights, and plan upcoming tasks. These meetings allow students to collaborate, seek feedback, and refine their approaches.

Documentation: Students will document their work, including coding procedures, experimental methods, and findings, which will help them keep track of their progress and prepare them for writing research papers and reports.

Mentorship Sessions: Students will have one-on-one sessions with faculty mentors to receive guidance, ask questions, and discuss challenges. 

Presentations: Periodically, students will present their work to the team or at academic forums. This helps them develop their presentation skills and gain confidence in sharing their research with others.

Interdisciplinary Collaboration: Students will engage in activities integrating knowledge from various fields, encouraging them to think creatively and approach problems from multiple perspectives.

By participating in these activities, students will gain a comprehensive understanding of AGI, develop practical skills, and prepare for future academic, professional, and start-up endeavors.

Hybrid

Dr. Razvan Voicu, rvoicu@kennesaw.edu

Dr. Muhammad Tanveer, mtanveer@kennesaw.edu

This project focuses on the design, modeling, and control of a walking robot intended to serve as a personal assistant within indoor environments. The primary objective is to develop an affordable robotic system by minimizing the degrees of freedom and the number of actuators required for basic locomotion. The initial phase aims to achieve stable straight-line walking, with future phases expanding the robot鈥檚 capabilities to include turning and stair climbing. The development process involves CAD design, 3D printing, and the integration of servomotors and microcontrollers for precise control. This project lays the groundwork for a cost-effective, functional robotic assistant tailored for indoor applications.

• CAD design
• 3D printing
• Microcontrollers

• Weekly reports
• 3D printing
• Programing

Face-to-Face

Dr. Amir Ali Amiri Moghadam, aamirimo@kennesaw.edu

Dr. Turaj Ashuri, tashuri@kennesaw.edu