This paper exploits the origins of artificial neural networks (ANN s) based on approximation theory, to refocus efforts on data transformation, and away from the exclusive attention on the development of more and more complex architectures. Machine learning (ML) networks efficiently accept raw input data and determine their own features for the training process. Features are chosen to optimize accuracy, but typically are not designed to be robust, leaving the network susceptible to noise. Thus, a case is made for the reintroduction of data transformation techniques, through an intelligent algorithm, to enhance the robustness of the ML networks. In a sense, the science and mathematics of AI algorithms must provide a path for the accurate, reliable, and rapid deployment of intelligent algorithms without an over-reliance of technological prowess such as inexpensive bandwidth and computing power. We developed an algorithm for image classification based on intelligent geometric transformations, which forms the input data for any neural network architecture of choice. Our results show that adopting intelligent data transformations for pre-processing network input leads, in comparison to a conventional raw image input convolutional neural network, to a more robust model to both random and adversarial noise, offering network designers enhanced control over the trade-off between accuracy and robustness.

Children with autism spectrum disorder (ASD) frequently engage in severe destructive behavior that presents significant risks to themselves and others, poses substantial barriers to community integration, and results in high familial and societal financial impact. Despite the efficacy of behavior analytic (BA) interventions for decreasing destructive behavior, to produce meaningful outcomes in the natural environment, treatment effects must transfer to parents. Parents often experience in-person training barriers, such as time, financial burden, transportation, and childcare, as well as concerns with the quality of training delivered, such as unrealistic and uncomfortable training with therapists. This paper presents preliminary results from a pilot test of a prototype of a virtual reality parent training tool intended to reduce access and quality barriers for parents with children with ASD who engage in severe destructive behavior.

Surgical education for residents is provided through observership and participation with attending surgeons, cadaveric sessions and use of textbook illustrations. This paper describes the development of virtual medical instruments as a flexible, safe, and scalable learning option that can provide real-time feedback for the resident and increase entrustability by the attending surgeon when the resident is in the operating room. In orthopedic surgery, total hip arthroplasty (THA) is reproducible and hence was chosen as the simulated training surgery. The virtual medical instruments developed for this research is set in a fully immersive 3D virtual environment that can allow for innovative ways to train students and provide a new way of experiential education. With the goal of making the training anatomically accurate, users can interact with the virtual operating environment in real-time to ensure proper instrument usage. The virtual procedure also provides realistic visualization of the surrounding operating room and anatomical environment around the surgery site, marking important landmarks to the surgeon to enable effective surgical training.

A multidisciplinary team of engineering faculty members at Rowan University are integrating digital imaging technology (DIT) into their undergraduate engineering curriculum.This exciting effort is based upon the experience and interest of faculty to promote new topics and innovative methods of teaching.The work is an effort to provide students with digital imaging experiences that make them ready for the marketplace.Projects involve the development of digital imaging experiements and curriculum and also the creation of a leading edge digital imaging laboratory/studio.This studio will facilitate the use of nontraditional learning approaches that encourage interactive learning, team building, and creative problem solving among students and instructors.A number of hands-on visual experiments are being developed and used to introduce students to the multidisciplinary engineering principles and use of DIT.Activities have also been developed for K-12 outreach.

Hip implants are extremely common procedures that are performed to relieve pain and restore function to the hip joint. Historically, most implants would last for the duration of the patient’s life, approximately 15 years after implantation; however, due to medical advancements patients are living longer and outliving the life of their implant. The most common cause for implant failure is the failure of the bond between the implant and the bone, occurring due to the translation or rotation of the implant. Once an implant has failed, a very invasive, costly, and painful revision surgery is required. There is significant advantage in the early detection of implant loosening. This paper presents a radial basis function based image processing technique to detect minute 3-D rotations of a hip implant from 2-D X-ray images. Comparing these rotations for a particular hip implant over time can alert orthopedic surgeons of trends that might lead to impending gross loosening of the implant and enable early correction.

The hallmark of the Rowan College of Engineering undergraduate program is to provide effective laboratory based instruction that illustrates important scientific concepts. This paper presents the results of an effort by the Department of Electrical and Computer Engineering at Rowan University to configure a novel method of teaching the junior level Communications (COMM), Digital Signal Processing (DSP) and Very Large Scale Integration (VLSI) courses under a common laboratory framework. These three courses are taken concurrently during the spring semester of the junior year. The described interdisciplinary experiments cut across individual course boundaries and integrate hands-on experience and software simulation. Software is integrated with the experiments through MATLAB and SIMULINK, C/C++ and Mentor Graphics.

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Session: 2793 Multidisciplinary Research using Nondestructive Evaluation Shreekanth Mandayam, Kauser Jahan and Douglas Cleary Rowan University, Glassboro Abstract A major objective of the Junior/Senior Engineering Clinics at Rowan University is to introduce students to open-ended engineering projects. All engineering students from the four engineering disciplines, namely Civil, Chemical, Electrical and Mechanical share a common engineering clinic class. The Junior/Senior Engineering Clinics, part of the innovative 8-semester Engineering Clinic sequence, provides the venue for multidisciplinary student teams to engage in semester-long design and development projects. These projects are typically funded by local industry, faculty research grants or departmental budgets. The clinic projects are crucial in developing the design, problem solving and project management skills that are often absent in the traditional engineering coursework. They further reinforce communication skills both oral and written. This paper focuses on the details of successful multidisciplinary research on non- destructive evaluation using engineering undergraduates. Introduction Rowan University is a regional state university committed to teaching and community service. The enrolment is approximately 9,000 students. The College of Engineering at Rowan University was initiated in 1996 as a result of a $100 million donation in 1992 from the Rowan Foundation. The engineering faculty use innovative methods of teaching and learning to better prepare students for entry into a rapidly changing and highly competitive marketplace1-4. Key program features include: (a) creating inter- and multi-disciplinary experiences through collaborative laboratories and coursework; (b) stressing total quality management (TQM) as the necessary framework for solving complex problems; (c) incorporating state-of-the-art technologies throughout the curricula; (d) and creating continuous opportunities for technical writing and communication. To best meet these objectives, the four engineering programs of Chemical, Civil, Electrical, and Mechanical Engineering have common engineering clinic classes throughout their programs of study, in which undergraduates work in teams on hands-on open-ended projects. The Engineering Clinics The purpose of the clinic classes is to provide engineering students with a hands-on, multidisciplinary experience throughout their college education. The freshman clinic focuses on primary principles, measurements, and competitive assessment. In the second semester, student teams take on semester long projects involving reverse engineering and/or engineering process exploration. The sophomore clinic focuses on design taught from the viewpoint of the four engineering disciplines represented at Rowan University: chemical, civil and environmental, electrical & computer, and mechanical. In the second semester, students work in teams on well- defined semester long design projects. The junior and senior clinics emphasize multidisciplinary Proceedings of the 2001 American Society for Engineering Education Annual Conference & Exposition Copyright  2001, American Society for Engineering Education

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Session 1454 The NCIIA Venture Capital Fund at Rowan University Anthony J. Marchese, John L. Schmalzel, John C. Chen, T.R. Chandrupatla, Kevin Dahm, Shreekanth A. Mandayam, Ravi P. Ramachandran, and Paris von Lockette College of Engineering Rowan University 201 Mullica Hill Rd. Glassboro, NJ 08028-1701 Abstract - The 8-semester Engineering Clinic sequence at Rowan University provides the venue for multidisciplinary student teams to engage in semester-long design and development projects. The majority of these projects are funded by local industry, faculty research grants or departmental budgets. Clearly, projects such as these are central to developing the design, problem solving and project management skills that are lacking in the traditional engineering coursework. Often miss- ing, however, in the industry and faculty sponsored design projects, is the spirit of invention, inno- vation and entrepreneurship. One way to promote the entrepreneurial spirit is to provide students with the opportunity to propose their own original enterprises. Accordingly, funding from the Na- tional Collegiate Inventors and Innovators Alliance (NCIIA) has created a Venture Capital Fund, specifically ear-marked for the development of original inventions by multidisciplinary student teams within the Junior and Senior Engineering Clinics. Funding of up to $2500 per student team per semester is competitively awarded based on student-generated proposals to the Venture Capital Fund. To qualify for funding, student teams must propose, plan and implement an original, semes- ter-long product development enterprise. The product idea must be successfully designed, devel- oped and prototyped in a single semester. The latter criterion is possible given the unique rapid prototyping facilities available at Rowan University, which include a stereolithography machine, a multi-jet modeling rapid concept modeler, a rapid circuit prototyping system and multiple consumer appliance test stations. To date, ten projects have been funded through the Venture Capital Fund. These projects include a Portable MP3 Player, a 3COM Palm® RS232 Protocol Analyzer, an Automated Synchronized Spinning Exercise Cycle, a Coating Thickness Monitor, a Linear Combi- nation Guitar Effects Processor, a Hybrid Rocket Motor Demonstrator, a Dorm-Sized Air Condi- tioner, a Hurricane Roof Vent and an Enhanced Four-Wheel Drive Suspension. Introduction In 1992, the local industrialist Henry M. Rowan made a $100 million donation to the then Glass- boro State College in order to establish a high-quality engineering school in southern New Jersey. This gift has enabled the university to create one of the most innovative and forward-looking engi- neering programs in the country. The College of Engineering at Rowan University is composed of

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Session 3215 Digital Imaging Activities for Civil Engineering Students Kauser Jahan, Shreekanth Mandayam, Beena Sukumaran and Yusuf Mehta Rowan University, College of Engineering Glassboro, NJ 08028 Abstract Digital imaging is an exciting field with applications in all areas of engineering. It currently represents one of the major research and development focus areas with sales exceeding 10 billion dollars per year. The technology has also become a part of our daily lives through televisions, cameras, scanners and medical X-rays. Engineers play an important and expanding role in this exciting field, yet undergraduate engineering students in civil and environmental engineering are rarely exposed to digital imaging through their coursework. The College of Engineering at Rowan University received funding from NSF to integrate digital imaging technology (DIT) in our undergraduate engineering curriculum. Faculty from all engineering disciplines with expertise in DIT participated in this exciting project to develop hands-on experiments for undergraduate engineering students. Experiments developed were such that all engineering disciplines would benefit from the endeavor. Certain digital imaging experiments have generated a lot of excitement in the Civil and Environmental Engineering program as many of the laboratory experiments are extremely traditional and are required to follow standard methodology. It is anticipated that other institutions will adopt the experiments that were developed as all educational materials are provided through a dynamic website. Introduction The College of Engineering at Rowan University received funding to establish a Digital Imaging (DI) laboratory and develop digital imaging course material by a team of Rowan faculty. Faculty with expertise in digital imaging technology from all engineering disciplines have developed hands-on experiments that can be readily used by various engineering and science disciplines. Funding was obtained from the National Science Foundation to purchase equipment to strengthen our DI laboratory and also to develop innovative educational material. Attention was given to develop material appropriate for a broad audience that includes K-12 educators/students and college students from science and engineering. The College of Engineering at Rowan University encourages faculty to integrate innovative teaching methods to expose students to contemporary topics. One such topic that is gaining momentum and popularity is digital imaging. This is a rapidly growing field with numerous applications ranging from consumer products, health services to research in academia. The new Proceedings of the 2005 Annual American Society for Engineering Education Conference. Copyright © 2005, American Society for Engineering Education

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Session 2632 Real Electromagnetics for Real Engineers – Really! Shreekanth A. Mandayam and Robert R. Krchnavek Rowan University Abstract This paper describes a sequence of classes – Engineering Electromagnetics I and II that is offered every Fall semester to Junior-level Electrical & Computer Engineering students at Rowan University. The instructors were motivated by a strong desire to make the learning of electromagnetics relevant – not only to other concurrent and subsequent engineering classes that the students take, but also to post-baccalaureate experiences in industry and graduate school. Moreover, since this course has long been feared by students as one of the toughest in the curriculum, the instructors tried to make leaning electromagnetics fun. Instructional techniques that were employed by the professors were based on a significant laboratory component that included numerical modeling, visualization and experimentation. This paper describes classroom/laboratory activity during the Fall 2000 semester offering of this course sequence. I. Introduction One of the unique challenges in the new Electrical & Computer Engineering program at Rowan University is to create and effectively deliver courses in the curriculum in 7-week integrated laboratory-lecture modules. These courses complement the semester-long design projects known as “Clinics” that students are required to take every semester of their curriculum. As a team of instructors who teach the Engineering Electromagnetics (EEMAG) I and II sequence, we were motivated by a desire to create a set of courses, that require students to do real and relevant engineering electromagnetics – and utilize these skills effectively in later courses and clinic projects. It is difficult to tackle all topics in a 7-week period so care must be taken to emphasize key topics and strengthen understanding through real-world laboratory exercises. We present some examples of a successful implementation of these objectives in this paper. We discuss numerous real-world applications that are studied during our single semester sequence of courses. We also show how the topics covered in the EEMAG I course are utilized in other courses/projects in the curriculum. In the first seven weeks of the semester, EEMAG I covers electrostatics, magnetostatics and quasistatics – details are provided in the course website1. In the second half of the semester, in EEMAG II, students tackle time-varying electromagnetic fields. Each of these courses contains an integrated laboratory component. The class meets every week for three 1-hour lecture periods and Proceedings of the 2001 American Society for Engineering Education Annual Conference & Exposition Copyright  2001, American Society for Engineering Education

Large scale distributed visualizations are routinely used by organizations in both the commercial and government sectors for training and simulation. These simulations are of particular importance in the research associated with the United States Federal Aviation Administration's current work on updating the National Airspace System to the Next Generation Air Transportation System. This new system will include the integration of unmanned aerial systems into civil airspace for routine flights.In this paper we propose a system for integrating unmanned aerial system visual observers into the distributed simulation capability of the Federal Aviation Administration using largescale virtual reality systems. We demonstrate the replication of terrain surrounding flight tests in virtual environments and the generation of the observer's views from both ground-based and airborne scenarios.

This paper discusses various strategies for characterizing three-dimensional particle morphology of granular media for use within the Discrete Element Methods (DEM) framework. The method utilized for three-dimensional shape characterization was performed on rounded Michigan Dune sand and more angular Daytona Beach sand. The feasibility of using Optical Microscope images for particle reconstruction, since these are the most inexpensive images to acquire, are validated against results from Optical Tomography and X-ray Tomography methods, which are more accurate. The particles reconstructed using this methodology can be captured in DEM by a clustering technique where several circular particles are clumped together. Numerical simulation of dry pluviation are performed to study the effect of grain shape obtained using the clustering algorithms on soil fabric and as validation of the process. Daytona Beach sand, Michigan Dune sand and glass beads are modeled in DEM and it is observed that soil fabric obtained from dry pluviation is strongly dependent on particle morphology.

Three dimensional tools for anatomical and radiological education for medical students are not novel. However, there has been limited ability to apply these tools into clinical practice. We speculate the reason for this situation is that although anatomical education software exists for a myriad of devices, and multiple applications exist for hand held devices, these platforms do not provide for intuitive correlation of clinical information from multiple diagnostic imaging procedures, nor do they provide users with any measure of prognostic capability. In this paper, we demonstrate the development of a virtual scalpel in the 3-D, immersive, navigable and interactive environment provided by a CAVE™. We propose that such an environment allows for the integrated visualization of medical images obtained from multiple radiological imaging platforms including CT, MRI, and PET. We intend to show such a system is advantageous not only for anatomical education but also for clinicians as a useful tool in surgical practice.

Valves play a critical role in rocket-engine test stands because they are essential for the cryogen transport mechanisms that are vital to test operations. Sensors that are placed on valves monitor the pressure, temperature, flow rate, valve position, and any other features that are required for diagnosing their functionality. Integrated system-health management (ISHM) algorithms have been used to identify and evaluate anomalous operating conditions of systems and subsystems (e.g., valves and valve components) on complex structures, such as rocket test stands. In order for such algorithms to be useful, there is a need to develop realistic models for the most common and problem-prone elements. Furthermore, the user needs to be provided with efficient tools to explore the nature of the anomaly and its possible effects on the element, as well as its relationship to the overall system state. This paper presents the development of an intelligent-valve framework that is capable of tracking and visualizing events of the large linear actuator valve (LLAV) in order to detect anomalous conditions. The framework employs a combination of technologies, including a dynamic data exchange data-transfer protocol, autoassociative neural networks, empirical and physical models, and virtual-reality environments. The diagnostic procedure that is developed has the ability to be integrated into existing ISHM systems and can be used for assessing the integrity of rocket-engine test-stand components.

The shear properties of natural granular particles such as sand are significantly dependent on the shapes of the particles in the mixture. This is important from a practical viewpoint, because a measurement and characterization technique for the 3-D shapes of such particles can lead to an improved understanding of soil stability and influence the design of structural foundations. Previous techniques that have been developed for this purpose have proven to be complex, and the associated instrumentation has proven to be expensive. Furthermore, conventional 2-D shape measurement and description methods do not readily lend themselves to parsimonious 3-D representations. The situation is further complicated by the fact that, to parameterize the relationship between shape and shear characteristics, a single numerical descriptor is required to model the 3-D shapes of multiple particles in a natural sand particle mixture. This paper describes an optical tomography technique for the measurement of particle data that is then characterized using statistical 3-D shape descriptors. The algebraic reconstruction technique (ART) is used to synthesize 3-D particle shapes from 2-D tomography projections. It is shown that the measurement and characterization techniques used can provide distinct features for differently shaped particle mixtures and can be used to synthesize 3-D composite particles representative of the entire mix. The novelty of the technique described in this paper is that numerical shape descriptors can be obtained for not only a single 3-D object but also an entire collection of 3-D objects. Furthermore, the statistical nature of the 3-D shape descriptor of a particle mixture can be used to synthesize a mixture containing an arbitrary number of particles that have similar but not identical shapes. Results demonstrating the efficacy of the method on a set of natural sand particle mixtures are presented.

To keep up with rapidly advancing technology, numerous innovations to the electrical and computer engineering (ECE) curriculum, learning methods and pedagogy have been envisioned, tested, and implemented. It is safe to say that no single approach will work for all of the diverse ECE technologies and every type of learner. However, a few key innovations appear useful in keeping undergraduate students motivated to learn, resilient to technology evolution, and oriented amid the overload of new information and ECE applications. Engineering clinics, similar to their medical clinic counterparts, provide project-based experiences within the core of an ECE education that enable transformation of the entire curriculum toward an outcomes-oriented, student-centered, total-quality environment. Clinics and project-based learning approaches build skills that give the students confidence and motivation to continuously self-learn and adapt as the technologies around them give way to new, more effective paradigms. Perhaps more importantly, engineering clinic experiences provide numerous opportunities for students to experience the holism of true engineering problem-solving approaches and the ranges of potential technology solutions. This paper reviews the clinic innovations that will enable ECE education to become more effective in the midst of the present plethora of information and technology. Assessment results are provided and are very encouraging. This paper concludes that agile learning environments, created to graduate engineers who can be rapidly productive in the professional and research worlds, are enhanced by clinic and/or project-based learning experiences in the ECE curriculum.

It has been shown that the flow and shear characteristics of granular particles such as soils are significantly dependent on the shape of the particles. This is important from a practical viewpoint because a fundamental understanding of granular behavior will lead to an improved understanding of soil stability and influence the design of structural foundations. Furthermore, the calculation of soil stability and, consequently, structural stability is particularly useful during earthquake events. In previous work, we have demonstrated the applicability of X-ray and optical tomography measurements for characterizing 3-D shapes of natural sands and manufactured granular particles. In this paper, we extend the work to measure the arrangement and the orientation of an assemblage of such particles. A combination of X-ray computed tomography (CT) for measuring the coordinates of the individual particles and an iterative adaptive thresholding technique for computing the local variations in porosity is employed to generate porosity maps. Such maps can be used to gain a more fundamental understanding of the shear characteristics of granular particles. In this paper, we demonstrate the success of our technique by exercising the method on several sets of granular particles-glass beads (used as a control), natural Michigan Dune and Daytona Beach sand, and processed Dry #1 sand.

Granular material packing is of considerable importance when considering the stability and shear strength of granular media. In this study, granular material packing at the grain scale is studied to see how packing is influenced by inherent particle characteristics such as shape, angularity and surface texture. Studies will show clear evidence of the influence of these factors on the granular packing obtained. Materials tested include glass beads, natural sands and a manufactured sand of varying shape, angularity and surface texture. X-ray CT is employed for imaging and 3-D volumetric reconstruction of sample assemblages. Image and volumetric processing routines are then performed on these reconstructions to measure local variations in packing density and generate density maps. In this paper, we demonstrate the success of our technique by exercising the method on several sets of granular particles.

Anomalous indications in monitoring equipment onboard U S. Navy vessels must be handled in a timely manner to prevent catastrophic system failure. The development of sensor data analysis techniques to assist a ship's crew in monitoring machinery and summon required ship-to-shore assistance is of considerable benefit to the Navy. In addition, the Navy has a large interest in the development of distance support technology in its ongoing efforts to reduce manning on ships. In this paper, we present algorithms for the detection of anomalous events that can be identified from the analysis of monochromatic stationary ship surveillance video streams. The specific anomalies that we have focused on are the presence and growth of smoke and fire events inside the frames of the video stream.The algorithm consists of the following steps. First, a foreground segmentation algorithm based on adaptive Gaussian mixture models is employed to detect the presence of motion in a scene. The algorithm is adapted to emphasize gray-level characteristics related to smoke and fire events in the frame. Next, shape discriminant features in the foreground are enhanced using morphological operations. Following this step, the anomalous indication is tracked between frames using Kalman filtering. Finally, gray level shape and motion features corresponding to the anomaly are subjected to principal component analysis and classified using a multilayer perceptron neural network.The algorithm is exercised on 68 video streams that include the presence of anomalous events (such as fire and smoke) and benign/nuisance events (such as humans walking the field of view). Initial results show that the algorithm is successful in detecting anomalies in video streams, and is suitable for application in shipboard environments. One of the principal advantages of this technique is that the method can be applied to monitor legacy shipboard systems and environments where high-quality, color video may not be available.

Integrated Systems Health Management (ISHM) consists of processes managing erroneous conditions that systems may encounter during their operational life by either designing out failures early on or defending and mitigating any possible failures. A successful implementation of ISHM consists of the following four components: data sensors, computations, data sinks, and visualization modules. In this paper, we explore the use of virtual reality (VR) platforms as a candidate for developing ISHM visualization modules. VR allows for a complete and spatially accurate 3-D model of a system to be displayed in real time. It provides a medium for improved data assimilation and analysis through its core tenants of immersion, interaction, and navigation. Furthermore, VR allows for integrating graphical, functional, and measurement data in the same platform-providing for the development of subsequent risk-analysis modules. The research objectives of this paper are focused on creating a detailed visual model of a multisensor rocket engine test facility inside a VR platform and demonstrating the capability of the VR platform in integrating graphical, measurement, and health data in an immersive, navigable, and interactive manner. A human-based performance evaluation of the VR platform is also presented. These research objectives are addressed using an example of a multisensor rocket-engine portable test stand at the National Aeronautics and Space Administration (NASA) Stennis Space Center's E-3 test facility.