Steven Corns

Stream gauge height (water level) is a significant indicator for forecasting future floods. Flooding occurs when the water level exceeds the flood stage. Predicting imminent floods can save lives, protect infrastructure, and improve road traffic management and transportation. Deep neural networks have been increasingly used in this domain due to their predictive capabilities in capturing complex features and interdependencies. This study employs four distinct models—Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), transformer, and LSTNet—with MLP serving as the baseline model to forecast water levels. The models are trained using data from 20 distinct river gages across the state of Missouri to ensure consistent performance. Random search optimization is employed for hyperparameter tuning. The prediction intervals are set at 4, 6, 8, and 10 (each interval equivalent to 30 min) to ensure that performance results are robust and not due to random weight initialization or suboptimal hyperparameters and are consistent throughout different prediction intervals. The findings of this study indicate that the LSTNet model leads to a better performance than the other models, with a median RMSE of 0.00724, 0.00959, 0.01204, and 0.01230 for the 4, 6, 8, and 10 intervals, respectively. As climate change leads to localized storms driven by atmospheric shifts, water level fluctuations are becoming increasingly extreme, further exacerbating data drift in real-world datasets. The LSTNet model demonstrates superior performance in terms of RMSE, MAE, and the correlation coefficient across all prediction intervals when forecasting water levels under data drift conditions.

The IEEE Computational Society (CIS) offers many financially-sponsored conferences each year. All of these depend on the hard work and effort of volunteers who propose and then organize these events in the pursuit of a healthy exchange of information and improvement in the application and theory of computational intelligence approaches. The last few years in particular have been a challenging time for conferences as the pandemic required rapid conversion to virtual programming. Only now are we finally seeing a return to largely in-person events with some hybrid components. The IEEE CIS Conferences Committee and Administrative Committee recently approved a motion to list the general chairs, program chairs, and financial chairs for IEEE CIS financially-sponsored conferences in IEEE Computational Intelligence Magazine on an annual basis as a way of recognizing these volunteers for their service. Your efforts are definitely appreciated and thank you on behalf of the society!

Asphyxiation associated with metabolic acidosis is one of the common causes of fetal deaths. The paper aims to develop a feature extraction and prediction algorithm capable of identifying most of the features in the SISPORTO software package and late and variable decelerations. The resulting features were used for classification based on umbilical cord pH data. The algorithms developed here were used to predict cord pH levels. The prediction system assists the obstetricians in assessing the state of the fetus better than the category methods, as only about 30% of the patients in the pathological category suffer from acidosis, while the majority of acidotic babies were in the suspect category, which is considered lower risk. By predicting the direct indicator of acidosis, umbilical cord pH, this work demonstrates a methodology, which uses fetal heart rate and uterine activity, to identify acidosis. This paper introduces a forecasting model based on deep learning to predict heart rate and uterine contractions, integrated with the classification algorithm, resulting in a robust tool for predictive fetal monitoring. The hybrid algorithm resulted in a model capable of providing future conditions of the fetus, which obstetricians can use for diagnosis and planning interventions. The ensemble classification algorithm had a test accuracy of 85% (n = 24) in predicting fetal acidosis on the features extracted from the cardiotocography data. When integrated with the classification model, the results from the prediction model (long short-term memory network) can effectively identify fetal acidosis 2 or 4 min in the future.

This paper proposes a framework using a community maturity level metric to determine the integration readiness of interface elements in a particular network cluster. As a proof of concept this methodology is applied to an aircraft seating system to assess the readiness of complex interfaces before proceeding to full‐scale production and systems integration. A multi‐objective genetic algorithm, MOGA‐Net, is coupled with the Newman‐Girvan modularity metric as a clustering algorithm. This algorithm identifies system elements grouped by common interfaces, referred to as community clusters. The TRL and IRL values for these elements is then used to calculate an overall community maturity level. The achieved performance in these clusters is then compared to the target performance to determine overall maturity of the interfaces. This is compared to other system readiness metrics and interface readiness metrics as applied to the aircraft seating system and was found to be more consistent with subject matter expert evaluations during the critical design review. This gives a better representation of the true readiness of system interfaces before entering design reviews to reduce overall integration risks.

Two Semester Agile Systems Engineering Design Course: Investigation and exploration of “Immersive” training technologies Cihan H Dagli, Steve Corns, Ivan Guardiola Engineering Management and Systems Engineering Department Sriram Chellappan Computer Science Department Maceij Zawodniak Electrical and Computer Engineering Department Missouri University of Science and Technology Rolla, Missouri 45409This paper discusses an immersive teaching curriculum developed to respond to a DoD problemarea identified as “Immersive Training Technologies”. It focuses on engineering students at thesenior undergraduate and first-year graduate levels. A set of two capstone courses are updatedand offered consecutively during the fall 2011 and spring 2012 semesters. The courses entitled“Systems Engineering Analysis” and “Physical Artifact Creation and Validation” are taught overthe period of one academic year impacting 30 students directly per semester, including 20 off-campus and 10 on-campus students. Another 10 students from a parallel section of the firstcourse are also impacted indirectly.Systems Engineering, Electrical and Computer Engineering, Computer Science, and Mechanicaland Aerospace Engineering are the main disciplines required for completion of the courseproject. The project selected culminates in the development of an upgrade of a vest designed inthe previous academic year that is capable of simulating real battlefield scenarios through the useof simulated live fire. The scenarios simulated include getting shot, getting hit, and minorrestriction. In addition, the pose of the student along with spatial location in the trainingenvironment are considered to determine appropriate cultural interaction in the simulation. Thechoice of proper components is determined by a guided trade study. . The students undertook thedevelopment of tracking through radio location, which involves the use of triangulation, anddirect application of mathematical models to determine localization of a user within anenvironment. The radiolocation is comprised of a fixed wireless network. The network activelycollates and collects data from the environment and is summarized and sent to the main controlfor analysis. The goal is to track individual within the environment for the purpose of observingsocial interactions. The tracking supplies training potentials in organization, tactics, socialinteraction, and hazardous situation avoidance. This is one part of two, in which, first tracking isaccomplished through radiolocation. Secondly, the data gathered must be analyzed and patternmatching be employed to detect hazardous situations, as well as train soldiers in the ways ofpreventive actions regarding social interactions and operations near or within civilian groups.The majority of the students’ development is comprised of transmission and reception controlsystems and the interfaces with other systems. The primary objective is to introduce students tothe complexity of modern systems, to the pitfalls of system designs, and to transfer knowledgeon how to deal with the complexity and pitfalls by using systems engineering processes, tools,and concepts. The primary contribution of this paper to systems engineering pedagogy is in theincrease of student knowledge gained regarding the developing of a small-scale system thatcould be realized as a useful, state of the art prototype. Students are attuned to the intricacies thatcomprise systems engineering of a deliverable product, in conjunction with the participation ofindustry mentors from the Boeing Company, the students are fully exposed to all constituents ofmodern engineering.

Distributed power generation can lead to overvoltage conditions, potentially damaging devices connected to the electrical grid. A method to improve the management of distributed power is presented to limit damaging overvoltage conditions using a transactive energy market and a Tabu Ant Colony Optimizer to manage activity on the distribution network. Overvoltage situations representing the intermittent power contributions from distributed sources were modeled on this network, and the results of current control methods were compared to those obtained using the developed Tabu Ant Colony Optimizer. Existing real time control methods resulted in overvoltages exceeding six percent above nominal, while the Tabu Ant Colony Optimizer resulted in overvoltage of less than three percent. Using this automated energy market mechanism as a management layer for the distribution network demonstrates how computational intelligence approaches can assist engineering managers responsible for these complex systems.

Floods are a complex phenomenon that are difficult to predict because of their non-linear and dynamic nature. Therefore, flood prediction has been a key research topic in the field of hydrology. Various researchers have approached this problem using different techniques ranging from physical models to image processing, but the accuracy and time steps are not sufficient for all applications. This study explores deep learning techniques for predicting gauge height and evaluating the associated uncertainty. Gauge height data for the Meramec River in Valley Park, Missouri was used to develop and validate the model. It was found that the deep learning model was more accurate than the physical and statistical models currently in use while providing information in 15 minute increments rather than six hour increments. It was also found that the use of data sub-selection for regularization in deep learning is preferred to dropout. These results make it possible to provide more accurate and timely flood prediction for a wide variety of applications, including transportation systems.