Heather T. Bednarz, MS, OTR/L
Edward T. Bednarz III, Ph.D.
Adjustable Wheelchair and Pressure Redistribution System
Heather Bednarz is a registered and licensed Occupational Therapist who has dedicated her career to helping patients. She recognized a need for a continuously adjustable wheelchair system that would replace many discrete sizes of wheelchair widths currently on the market. Along with husband, Edward Bednarz, who is an Associate Professor at Wilkes University, and Mechanical Engineering students, a product was developed and patented to accomplish this goal.
Similarly, Heather, Edward and another group of students invented a pressure redistribution system that can be used on wheelchairs and other devices. The goal of this product is to alleviate pressure ulcers by actively monitoring and repositioning patients who are prone to sitting in one position for extended periods of time. This product was also developed and patented.
The co-inventors, who are also business partners, are actively looking to sell both patents to companies. Their dream is to see these products mass produced to help people.
Michael Evans, Ph.D, MSEd, RN, ACNS, CMSRN, CNE
Assistant Chief Academic Officer and an Associate Teaching Professor of Nursing
Penn State University
Using Swivl as Teaching Tool in Nursing Education
Swivl is a remote-controlled robotic video observation device that produces high quality audio and video. Recordings were made of faculty performing focused assessments and interventions, which allowed students to watch the videos countless times in BOX as they worked to perfect their assessments and skills. In addition, it helped save the nursing department money as the typical nursing DVD costs anywhere from $100-$400/piece. Moreover, we were able to use Swivl technology to record student simulations and then use the videos as part of the debriefing exercise where students could learn from their mistakes in a safe environment while working to provide safe, patient care.
In this case, Swivl technology enhanced our ability to record students as it followed the students through the simulation lab as they worked through the scenario, which was a definite limitation of our previous recording system (webcam). A sample recording will be shown during the presentation. Student feedback has been very positive, including statements such as “I love how I can watch my teachers do the assessment the right way as many times as I need too.” and “Utilizing Swivl in the simulation setting has allowed me to be aware of my interactions with the patient and colleagues.” In conclusion, Swivl technology has enhanced our abilities to educate our students in a fun and interactive way while improving their clinical reasoning and judgment skills as we strive to prepare well educated graduate nurses who can provide safe, competent care.
Martin Takac, Ph.D.
Reinforcement Learning in Engineering
In this talk, we briefly introduce Reinforcement Learning – a powerful machine learning tool used in many engineering fields. We will discuss two interesting applications of reinforcement learning (1) controlling stochastic supply chain (joint work with Prof. Snyder and supported by NSF grant in collaboration with Siemens Corporation, and (2) training multiple smart agents to communicate and collaborate to achieve given goals.
We will conclude the talk by describing a novel Corrective Reinforcement Learning Framework which allows training reinforcement learning policies (e.g. hand-crafted expert strategy).
Penn State Scranton
Penn State Scranton
Smart Machines: Myth and Mysteries
Modern technologies are driving the business world into the future. Disruption is now a constant state of existence and the pace of change is increasing. And while there are many technologies driving the modernization and fueling the current industrial revolution, most people walk blissfully through the world without understanding the underlying technologies. There are many myths and mysteries surrounding these technologies.
In this session we will discuss some of the underpinnings of the topics that will be covered at the conference, including smart machines, collaborative robots, artificial intelligence, machine learning, additive manufacturing, and autonomous equipment. This will include the technical and economic impacts of these technologies. We will show glimpses of the past of these technologies.
Historians generally agree that there have been three previous industrial revolutions and that we are now experiencing the fourth industrial revolution. We will explain the technologies that are the backbone of the modern industrial revolution and unravel the myths and mysteries surrounding them.
Benjamin Bishop, Ph.D., Professor
Professor of Computing Sciences
University of Scranton
Renée M. Hakim, PT, PhD, NCS, Professor
PT, PhD, NCS, Professor
University of Scranton
Haptic Devices to Improve Arm/Hand Function
Haptic devices collect input from the user while providing tactile feedback. These systems can be used to provide high repetition task-specific practice for patients with motor impairments. A system will be presented that focuses on functional task training (i.e., handwriting) for patients with arm/hand disorders. The system allows patients to improve dexterity by practice of writing using augmented feedback (haptic, visual, auditory) with or without the direct supervision of a physical therapist.
Del Lucent Ph.D.
Associate Professor of Physics
New Kids on the Blockchain: Protein Folding and Machine Learning on the Coronai Network
Protein folding is among the most vital of processes needed to sustain life. Unfortunately, biochemical and biophysical experiments struggle to produce a comprehensive, mechanistic understanding of this process. Although detailed computer simulations help to ameliorate this problem, conducting these simulations requires substantial computational resources and yields very large datasets which must be distilled using various machine learning strategies. In order to meet these increasing computational demands, we are among the first adopters of Coronai: a general purpose, decentralized grid computing protocol. Coronai allows for flexible and efficient access to distributed computing by using a cryptocurrency to incentivize participation and a blockchain to ensure validity of scientific results.
E. Thomas Pashuck, Ph.D. (Tommy)
Assistant Professor, Department of Bioengineering
Developing Cell-Responsive Biomaterials for Regenerative Medicine
Regenerative medicine is a multidisciplinary approach that combines chemistry, engineering, biology, and medicine to design therapies to replace or repair damaged or diseased tissue. These are generally optimized for a single cell type, even though every tissue in the body is made up of many different cells working together towards a biological function. Therapies aimed at restoring these tissues will need to be able to support several different cell types simultaneously and foster the complex relationships that exist during regeneration and homeostasis. The current question is how materials can be designed to specifically target different cell types within a single scaffold. This will require extensive control over the specificity as well as spatial and temporal control over the activity of biological factors. This talk will focus on using cell-specific protease activity to induce local changes the matrix that can be used to guide regeneration.
Michele M. McGowan, DBA, CPA, CIFHA
Associate Professor and Graduate Program Director, Healthcare Administration
Smart Machines in Healthcare – Teaching the Management Side of Major Investments
Everyone wants the latest and greatest new toys, but are they worth the investment? These purchases require a large outlay of resources, have a long-term impact on earnings, generally lack liquidity, and influence the organization’s capacity for providing services. As a result, these decisions are among the most important ones made. So how do we make good capital investments decisions? This session will share how at King’s College we educate future healthcare leaders on appropriate capital budgeting techniques, methods of risk adjustment and scenario and sensitivity analysis, and the importance of qualitative considerations in the decision-making process. The goal is to help prevent you from making poor investment decisions that can have a disastrous effect on your organization.
Chris Speicher, Ph.D.
Director of Entrepreneurship, Marywood University
Chief Visionary Officer, DartDrones, LLC
Drones : The Sky is No Longer the Limit
The Drone industry took off with great momentum in 2014. Today it has plateaued and is in a hold pattern waiting for technology on the ground to catch up to the technology in the sky. How far are we away from the Jetsons era? How long until Starbucks delivers right here, right now? Where to and how long?
DartDrones is the international leader in drone education and training. With over 50 flight instructors worldwide, DartDrones, trains entities from US Governement agencies and police and fire organizations to leading utility and oil and gas producers to major video production companies.
Joshua C. Agar, Ph.D.
Assistant Professor, Department of Materials Science and Engineering
Deducing Inference from Hyperspectral Imaging of Materials via Machine Learning
Characterization of materials relies on measuring their stimuli-driven response after perturbation by an external energy source. These measurements generally involve either continuously changing the magnitude of the perturbation or the bandwidth/energy of the response which is measured resulting in data which has sequential or temporal dependence. Recent advances in high-speed sensors have allowed spectroscopic measurements to be conducted using a multitude of techniques (e.g., electron microscopy, atomic force microscopy, etc.) which also have high-spatial resolution. Coupling spectroscopic characterization with imaging allows researchers to directly probe structure-property relations at relevant length and time scales.
Despite a boon in these multidimensional spectroscopic imaging techniques the size and complexity of the data being collected coupled with the dearth of downstream analysis approaches have limited the ultimate scientific contributions of these powerful experimental techniques. Here, we show how deep-recurrent neural networks can be used to automate the extraction of features physically-important phenomena concealed within “big” multichannel hyperspectral data into focus for interpretation. Specifically, we will discuss the broad applicability of this approach to experimental techniques ranging from piezoresponse measurement of ferroelectrics, discovery of new conduction mechanisms at charged domain walls, and atomically-resolved electron energy loss spectroscopic of functional interfaces.
The methodology developed paves the way for spectroscopic techniques wherein the conventional scientific methods of designing targeted experiments aimed at a specific hypothesis are supplanted by approaches which collect all seemingly relevant data, which can then be automatically interpreted to identify a hypothesis for empirical testing.
Professor of Art + Design
East Stroudsburg University
“Heavy Metal”- The Disruption of 3D Printing
Jill Murray, Ph.D.
EVP & Chief Innovation Officer
eSport. Smart Strategy.