No abstract

Laboratory practice is an important tool in the education of engineering students. The practical aspect of a laboratory-based education provides a tactile experience for students that allows students an opportunity to understand concepts and also prepare them for the engineering job market. One of the challenges faced by many institutions is that laboratory equipment and machines are costly and, as a result, a viable alternative option should be sought. This necessitates the adoption of virtual reality-based laboratory experiments that provide a laboratory-based instructional experience, similar to that of a real laboratory, yet utilizes a three-dimensional virtual simulation. This provides students with an opportunity to carry out experiments virtually and achieve instant results. In this study, a practical laboratory experience is provided through the use of a virtual reality simulation that is based on a real laboratory. Students are familiarized with the equipment through the provision of the real-world electronic bench equipment and simple electronic components resembling the real laboratory environment. The effectiveness of the virtual reality laboratory is studied using three sets of engineering students. The sets of students include those who have engaged in an actual laboratory experience, those who have experienced only the virtual reality-based laboratory environment, and a third group who has experienced both the real and the virtual reality laboratories. Using a common quiz, each set of students is assessed in their ability to identify and describe the uses of various laboratory equipment. Through the assessment, the viability of the virtual reality-based laboratory is studied regarding the effectiveness of it as an education tool. Recommendations are also made for institutions interested in designing similar experiences.

Missing values, irregularly collected samples, and multi-resolution signals commonly occur in multivariate time series data, making predictive tasks difficult. These challenges are especially prevalent in the healthcare domain, where patients vital signs and electronic records are collected at different frequencies and have occasionally missing information due to the imperfections in equipment or patient circumstances. Researchers have handled each of these issues differently, often handling missing data through mean value imputation and then using sequence models over the multivariate signals while ignoring the different resolution of signals. We propose a unified model named Multi-resolution Flexible Irregular Time series Network (Multi-FIT). The building block for Multi-FIT is the FIT network. The FIT network creates an informative dense representation at each time step using signal information such as last observed value, time difference since the last observed time stamp and overall mean for the signal. Vertical FIT (FIT-V) is a variant of FIT which also models the relationship between different temporal signals while creating the informative dense representations for the signal. The multi-FIT model uses multiple FIT networks for sets of signals with different resolutions, further facilitating the construction of flexible representations. Our model has three main contributions: a.) it does not impute values but rather creates informative representations to provide flexibility to the model for creating taskspecific representations b.) it models the relationship between different signals in the form of support signals c.) it models different resolutions in parallel before merging them for the final prediction task. The FIT, FIT-V and Multi-FIT networks improve upon the state-of-the-art models for three predictive tasks, including the forecasting of patient survival. * Equal contribution, randomly ordered.

No abstract

is an undergraduate Computer Engineering student from Wentworth Institute of Technology who will graduate in August of 2018. After the completion of his undergraduate degree, Bryon will attend the University of Massachusetts Amherst to pursue a Master's in Computer Science where he plans to focus on Artificial Intelligence.