SmarTex

SmartTex is a revolutionary textile wiring technology that transforms any fabric into a pressure responsive one. The technology relies on impregnating a novel electrically conductive polymer within textile fibers imparting the conductivity and pressure sensitivity characteristics to the textile. SmarTex technology is currently used for fabricating smart shoe insoles and multifunctional soldiers’ outfits.

Student: Mohamed Hassan
Faculty: Silvana Andreescu

Vision Controlled Prosthetic Hand

We introduce a vision-controlled prosthetic hand designed to mimic the performance, utility, aesthetics, and comfort of a natural hand. From sensor feedback, the embedded process can perform real-time image processing and distance approximation of objects. This prosthesis is customizable for a range of ages, maintains a low cost and power budget, and requires no specialized training in contrast to conventional EMG-based systems. The project will serve as a pilot for other upper/lower-limb prostheses and carry it forward to large-scale implementation and production.

Student: Md Abdul Baset Sarker
Faculty: Masudul Imtiaz

Behavioral Biometrics for Computer Authentication

Our technology provides additional security against online account takeovers through behavioral authentication to prevent transaction fraud and unauthorized access to private/corporate data. Our solution is seamless, frictionless and without any extra authentication steps or hardware. Compared to other multifactor authentication schemes, our solution significantly cuts down the authentication time by about 60 – 70% while providing stronger security.

Student: Ahmed Anu Wahab
Faculty: Daqing Hou

TherD-7

The TherD-7 team proposes an end-to-end 3D imaging system that enables 3D human body joint movement and skin surface temperature tracking through multi-modal markerless motion capture. The proposed technology fills a critical gap in enabling non-invasive full-body 3D thermographic analysis for performance assessment, and injury risk estimation, prevention, and treatment for target markets in sports science and medicine. Through intelligent application of computer vision and deep learning coupled with communications with sensor manufacturers, the team will work toward making precision multi-modal markerless systems affordable for rural healthcare, educational institutions and regional/intramural sports teams, expanding societal access.

Student: Noah Wiederhold
Faculty: Natasha Banerjee, Sean Banerjee

Project Output

Our innovation is an implantable haptic feedback device that allows a user better interaction and feedback from various sensory modules. The implantable nature increases the user’s ability to integrate the vibrations into a more natural sense over time; the natural neuroplastic capacity of the brain will allow a user an intuitive and integrated understanding of the linked device. Design constraints surrounding internal power storage are avoided and present an opportunity for modular sensor packages. Current applications include blood glucose monitoring, radiation dosimetry, and pseudo-echolocation using an array of implants.

Student: Quinn Mooney
Faculty: Masudul Imtiaz

HardLite: Real-Time Ransomeware Detection

Recent years have witnessed a surge in ransomware attacks. The technology we introduce is a real-time anomaly detection framework for ransomware detection. By using advanced machine learning methods, we are able to take into consideration the low-level hardware information to detect deviation in system behavior. Testing against various ransomware across multiple families, this technology has demonstrated exceptional detection accuracy. What’s more, this technology has good scalability with a built-in hierarchical design. Dr. Chen Liu is currently an associate professor in the department of electrical and computer engineering at Clarkson University. He has rich experience in cybersecurity defense techniques, especially on the interaction between hardware and system software.

Faculty: Chen Liu

MendNet

We introduce Mendnet, the first AI-powered algorithm to perform automated object repair. Using 3D scanning, artificial intelligence, and 3D printing, Mendnet automatically creates a repair solution for broken items. Our technology will provide repairs for consumer household items and recycling and manufacturing facilities alike, reducing waste and turning would-be trash into value.

Student: Nikolas Lamb
Faculty: Sean Banerjee, Natasha Banerjee

Face-Aware Capture System

The quality of the acquired raw face data is one of the main factors affecting the overall performance of face analysis and recognition systems. Low facial samples generate facial biometric artifacts, increase enrollment failure, and prevent the face recognition system from assigning the correct identity to a face, thus decreasing the system’s performance. Therefore, controlling the quality of the acquired facial data is essential to avoid the complexity of the recognition procedures and achieve a proper facial authentication system. Therefore, performing the quality assessment when capturing the facial data (real-time) could be a straightforward approach to addressing the problem. We provide a solution to capture the best quality images by implementing face-aware capture to give a completely open-source hardware solution. We developed a completed solution to provide real-time face-aware capture on embedded devices.

Student: Naveendumar Venkatawamy
Faculty: Masudul Imtiaz