2020 IEEE Frontiers in Education Conference (FIE), 2020
This Research Full Paper presents the approach of traditional engineering analysis techniques on ... more This Research Full Paper presents the approach of traditional engineering analysis techniques on education. Data mining techniques have been successfully employed to extract hidden information from large data sets within various contexts. We hypothesized that data mining techniques can similarly be applied to large educational data sets to extract and analyze patterns and create insights. Specifically, we examined the degree to which standard data mining techniques can distinguish between different student attention patterns in large lectures in which personal computers were actively used. Our data set consists of electronically captured student attention data (on-task, off-task) that was recorded at 20 second intervals throughout each course lecture over one semester. With Institutional Review Board (IRB) approval, methods involved capturing student data via a backend monitoring system to reduce student awareness of monitoring and reduce false behavior changes during data collection periods. The data were originally captured in the form of images (screenshots), and image processing techniques were applied to extract student attention patterns in the form of zero (off-task) and one (ontask). We conducted descriptive statistical analysis to add other features such as characterization information (e.g., total logged in attention, average class period attention to the recorded data sets). For the data mining analysis, we used three different supervised machine learning classification algorithms: Support Vector Machine (SVM), Decision Tree, and K-Nearest Neighbors (KNN) for classifying the students' dataset. We classified the students into one of four different classes based on their attention pattern in the lecture class. Before applying each classification algorithm, feature extraction was performed. For this purpose, we used Haar wavelets, Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA) dimensionality-reduction techniques before applying the classification algorithm. Their performance is compared. Our results indicate high classification accuracies can be obtained using these dimensional reduction algorithms followed by classification algorithms. Our result highlights the importance of applying traditional engineering analysis techniques to educational data in order to provide engineering education insights.
This paper examines target detection using a Linear Support Vector Machine (L-SVM). Traditional r... more This paper examines target detection using a Linear Support Vector Machine (L-SVM). Traditional radars typically use a Constant False Alarm Rate (CFAR) processor to adaptively adjust the detection threshold based on the fast-time return signal. The SVM formulation uses the same blockdiagram structure as the CFAR approach; however, data from the leading and lagging windows is directly used to classify each cell under test. The L-SVM method is compared to a Cell-Averaging CFAR (CA-CFAR) on simulated radar return signals with and without Swerling I targets. The results show that the L-SVM is able to detect very small SNR signals, while the CA-CFAR is unable to detect these signals below-10 dB SNR. In addition, the probability of detection and probability of false alarm for the L-SVM degrade much more gracefully than for the CA-CFAR detector for low-SNR targets.
When it comes to some essential abilities of autonomous ground vehicles (AGV), detection is one o... more When it comes to some essential abilities of autonomous ground vehicles (AGV), detection is one of them. In order to safely navigate through any known or unknown environment, AGV must be able to detect important elements on the path. Detection is applicable both on-road and off-road, but they are much different in each environment. The key elements of any environment that AGV must identify are the drivable pathway and whether there are any obstacles around it. Many works have been published focusing on different detection components in various ways. In this paper, a survey of the most recent advancements in AGV detection methods that are intended specifically for the off-road environment has been presented. For this, we divided the literature into three major groups: drivable ground and positive and negative obstacles. Each detection portion has been further divided into multiple categories based on the technology used, for example, single sensor-based, multiple sensor-based, and ho...
Fish species recognition is crucial to identifying the abundance of fish species in a specific ar... more Fish species recognition is crucial to identifying the abundance of fish species in a specific area, controlling production management, and monitoring the ecosystem, especially identifying the endangered species, which makes accurate fish species recognition essential. In this work, the fish species recognition problem is formulated as an object detection model to handle multiple fish in a single image, which is challenging to classify using a simple classification network. The proposed model consists of MobileNetv3-large and VGG16 backbone networks and an SSD detection head. Moreover, a class-aware loss function is proposed to solve the class imbalance problem of our dataset. The class-aware loss takes the number of instances in each species into account and gives more weight to those species with a smaller number of instances. This loss function can be applied to any classification or object detection task with an imbalanced dataset. The experimental result on the large-scale reef...
Standards for the fatigue testing of wearable sensing technologies are lacking. The majority of p... more Standards for the fatigue testing of wearable sensing technologies are lacking. The majority of published fatigue tests for wearable sensors are performed on proof-of-concept stretch sensors fabricated from a variety of materials. Due to their flexibility and stretchability, polymers are often used in the fabrication of wearable sensors. Other materials, including textiles, carbon nanotubes, graphene, and conductive metals or inks, may be used in conjunction with polymers to fabricate wearable sensors. Depending on the combination of the materials used, the fatigue behaviors of wearable sensors can vary. Additionally, fatigue testing methodologies for the sensors also vary, with most tests focusing only on the low-cycle fatigue (LCF) regime, and few sensors are cycled until failure or runout are achieved. Fatigue life predictions of wearable sensors are also lacking. These issues make direct comparisons of wearable sensors difficult. To facilitate direct comparisons of wearable sens...
An accurate and robust perception system is key to understanding the driving environment of auton... more An accurate and robust perception system is key to understanding the driving environment of autonomous driving and robots. Autonomous driving needs 3D information about objects, including the object’s location and pose, to understand the driving environment clearly. A camera sensor is widely used in autonomous driving because of its richness in color, texture, and low price. The major problem with the camera is the lack of 3D information, which is necessary to understand the 3D driving environment. Additionally, the object’s scale change and cclusion make 3D object detection more challenging. Many deep learning-based methods, such as depth estimation, have been developed to solve the lack of 3D information. This survey presents the image 3D object detection 3D bounding box encoding techniques, feature extraction techniques, and evaluation metrics of 3D object detection. The image-based methods are categorized based on the technique used to estimate an image’s depth information, and ...
Background: Wearable technology is used by clinicians and researchers and play a critical role in... more Background: Wearable technology is used by clinicians and researchers and play a critical role in biomechanical assessments and rehabilitation. Objective: The purpose of this research is to validate a soft robotic stretch (SRS) sensor embedded in a compression knee brace (smart knee brace) against a motion capture system focusing on knee joint kinematics. Methods: Sixteen participants donned the smart knee brace and completed three separate tasks: non-weight bearing knee flexion/extension, bodyweight air squats, and gait trials. Adjusted R2 for goodness of fit (R2), root mean square error (RMSE), and mean absolute error (MAE) between the SRS sensor and motion capture kinematic data for all three tasks were assessed. Results: For knee flexion/extension: R2 = 0.799, RMSE = 5.470, MAE = 4.560; for bodyweight air squats: R2 = 0.957, RMSE = 8.127, MAE = 6.870; and for gait trials: R2 = 0.565, RMSE = 9.190, MAE = 7.530 were observed. Conclusions: The smart knee brace demonstrated a higher...
IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018
Herein, we present a system for hyperspectral image segmentation that utilizes multiple class-bas... more Herein, we present a system for hyperspectral image segmentation that utilizes multiple class-based denoising autoencoders which are efficiently trained. Moreover, we present a novel hyperspectral data augmentation method for labelled HSI data using linear mixtures of pixels from each class, which helps the system with edge pixels which are almost always mixed pixels. Finally, we utilize a deep neural network and morphological hole-filling to provide robust image classification. Results run on the Salinas dataset verify the high performance of the proposed algorithm.
Opportunities to apply data mining techniques to analyze educational data and improve learning ar... more Opportunities to apply data mining techniques to analyze educational data and improve learning are increasing. A multitude of data are being produced by institutional technology, e-learning resources, and online and virtual courses. These data could be used by educators to analyze and understand the learning behaviors of students. The obtained data are raw data that must be analyzed, requiring educational data mining to predict useful information about students, such as academic performance, among other things. Many researchers have used traditional machine learning to predict the academic performance of students, and very little research has been conducted on the architecture of convolutional neural networks (CNNs) in the context of the pedagogical domain. We built a hybrid 2D CNN model by combining two different 2D CNN models to predict academic performance. Our sample comprised 1D data, so we transformed it to 2D image data to test the performance of our hybrid model. We compared...
2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2017
While the Choquet integral (ChI) is a powerful parametric nonlinear aggregation function, it has ... more While the Choquet integral (ChI) is a powerful parametric nonlinear aggregation function, it has limited scope and is not a universal function generator. Herein, we focus on a class of problems that are outside the scope of a single ChI. Namely, we are interested in tasks where different subsets of inputs require different ChIs. Herein, a genetic program (GP) is used to extend the ChI, referred to as GpChI hereafter, specifically in terms of compositions of ChIs and/or arithmetic combinations of ChIs. An algorithm is put forth to learn the different GP ChIs via genetic algorithm (GA) optimization. Synthetic experiments demonstrate GpChI in a controlled fashion, i.e., we know the answer and can compare what is learned to the truth. Real-world experiments are also provided for the mult-sensor fusion of electromagnetic induction (EMI) and ground penetrating radar (GPR) for explosive hazard detection. Our mutli-sensor fusion experiments show that there is utility in changing aggregation strategy per different subsets of inputs (sensors or algorithms) and fusing those results.
A deep-learning-based approach to estimating the number of coherent sources in radar is presented... more A deep-learning-based approach to estimating the number of coherent sources in radar is presented. A proper estimate of the number of sources in a signal enables improved angle-of-arrival (AoA) estimation common in applications such as radar, sonar, and communication systems. Many AoA estimators utilised in these areas require accurate estimates of the number of sources for enhanced performance. Herein, a robust method that performs well under the existence of coherent sources is developed. The proposed method is based on deep learning and it is shown to perform better than state-of-the-art versions of the Akaike Information Criteria (AIC), Minimum Description Length (MDL), and Exponentially Embedded Families (EEF) estimators, which employ spatial smoothing of the covariance matrix to handle coherent signals. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Autonomous Systems: Sensors, Processing, and Security for Vehicles and Infrastructure 2019, 2019
For autonomous vehicles 3D, rotating LiDAR sensors are often critically important towards the veh... more For autonomous vehicles 3D, rotating LiDAR sensors are often critically important towards the vehicle’s ability to sense its environment. Generally, these sensors scan their environment, using multiple laser beams to gather information about the range and the intensity of the reflection from an object. LiDAR capabilities have evolved such that some autonomous systems employ multiple rotating LiDARs to gather greater amounts of data regarding the vehicle’s surroundings. For these multi–LiDAR systems, the placement of the sensors determine the density of the combined point cloud. We perform preliminary research regarding the optimal LiDAR placement strategy on an off–road, autonomous vehicle known as the Halo project. We use the Mississippi State University Autonomous Vehicle Simulator (MAVS) to generate large amounts of labeled LiDAR data that can be used to train and evaluate a neural network used to process LiDAR data in the vehicle. The trained networks are evaluated and their performance metrics are then used to generalize the performance of the sensor pose. Data generation, training, and evaluation, was performed iteratively to perform a parametric analysis of the effectiveness of various LiDAR poses in the Multi–LiDAR system. We also, describe and evaluate intrinsic and extrinsic calibration methods that are applied in the multi–LiDAR system. In conclusion we found that our simulations are an effective way to evaluate the efficacy of various LiDAR placements based on the performance of the neural network used to process that data and the density of the point cloud in areas of interest.
M odern signal processing (SP) classes should provide a balance between theory and application as... more M odern signal processing (SP) classes should provide a balance between theory and application as well as use active learning exercises to engage students and facilitate learning. A new sensor processing course, Sensor Processing for Autonomous Vehicles (SPAV), was designed with two specific objectives: 1) to successfully engage students using active and collaborative learning and 2) integrate a state-of-the-art, physicsbased autonomy simulator into the class. The course was delivered to local and asynchronous distance students in spring 2020 at Mississippi State University (MSU). The MSU Autonomous Vehicle Simulator (MAVS) was used in the class. We also utilized three miniprojects to bring together theory and practice. We evaluated the course through student feedback. Results indicated that students viewed active exercises and the simulator as beneficial and useful, with multiple students describing those aspects as their favorite part of the course. Nearly all students (39 of 40) reported that they were engaged in the course.
This paper presents a retrospective of the benchmark testing methodologies developed and accumula... more This paper presents a retrospective of the benchmark testing methodologies developed and accumulated into the stretch sensor tool kit (SSTK) by the research team during the Closing the Wearable Gap series of studies. The techniques developed to validate stretchable soft robotic sensors (SRS) as a means for collecting human kinetic and kinematic data at the foot-ankle complex and at the wrist are reviewed. Lessons learned from past experiments are addressed, as well as what comprises the current SSTK based on what the researchers learned over the course of multiple studies. Three core components of the SSTK are featured: (a) material testing tools, (b) data analysis software, and (c) data collection devices. Results collected indicate that the stretch sensors are a viable means for predicting kinematic data based on the most recent gait analysis study conducted by the researchers (average root mean squared error or RMSE = 3.63°). With the aid of SSTK defined in this study summary and...
International Journal of Environmental Research and Public Health, 2020
Wearable sensors are beneficial for continuous health monitoring, movement analysis, rehabilitati... more Wearable sensors are beneficial for continuous health monitoring, movement analysis, rehabilitation, evaluation of human performance, and for fall detection. Wearable stretch sensors are increasingly being used for human movement monitoring. Additionally, falls are one of the leading causes of both fatal and nonfatal injuries in the workplace. The use of wearable technology in the workplace could be a successful solution for human movement monitoring and fall detection, especially for high fall-risk occupations. This paper provides an in-depth review of different wearable stretch sensors and summarizes the need for wearable technology in the field of ergonomics and the current wearable devices used for fall detection. Additionally, the paper proposes the use of soft-robotic-stretch (SRS) sensors for human movement monitoring and fall detection. This paper also recapitulates the findings of a series of five published manuscripts from ongoing research that are published as Parts I to ...
A novel wearable solution using soft robotic sensors (SRS) has been investigated to model foot-an... more A novel wearable solution using soft robotic sensors (SRS) has been investigated to model foot-ankle kinematics during gait cycles. The capacitance of SRS related to foot-ankle basic movements was quantified during the gait movements of 20 participants on a flat surface as well as a cross-sloped surface. In order to evaluate the power of SRS in modeling foot-ankle kinematics, three-dimensional (3D) motion capture data was also collected for analyzing gait movement. Three different approaches were employed to quantify the relationship between the SRS and the 3D motion capture system, including multivariable linear regression, an artificial neural network (ANN), and a time-series long short-term memory (LSTM) network. Models were compared based on the root mean squared error (RMSE) of the prediction of the joint angle of the foot in the sagittal and frontal plane, collected from the motion capture system. There was not a significant difference between the error rates of the three diff...
The purpose of this study was to use 3D motion capture and stretchable soft robotic sensors (SRS)... more The purpose of this study was to use 3D motion capture and stretchable soft robotic sensors (SRS) to collect foot-ankle movement on participants performing walking gait cycles on flat and sloped surfaces. The primary aim was to assess differences between 3D motion capture and a new SRS-based wearable solution. Given the complex nature of using a linear solution to accurately quantify the movement of triaxial joints during a dynamic gait movement, 20 participants performing multiple walking trials were measured. The participant gait data was then upscaled (for the SRS), time-aligned (based on right heel strikes), and smoothed using filtering methods. A multivariate linear model was developed to assess goodness-of-fit based on mean absolute error (MAE; 1.54), root mean square error (RMSE; 1.96), and absolute R2 (R2; 0.854). Two and three SRS combinations were evaluated to determine if similar fit scores could be achieved using fewer sensors. Inversion (based on MAE and RMSE) and plant...
Background: An induced loss of balance resulting from a postural perturbation has been reported a... more Background: An induced loss of balance resulting from a postural perturbation has been reported as the primary source for postural instability leading to falls. Hence; early detection of postural instability with novel wearable sensor-based measures may aid in reducing falls and fall-related injuries. The purpose of the study was to validate the use of a stretchable soft robotic sensor (SRS) to detect ankle joint kinematics during both unexpected and expected slip and trip perturbations. Methods: Ten participants (age: 23.7 ± 3.13 years; height: 170.47 ± 8.21 cm; mass: 82.86 ± 23.4 kg) experienced a counterbalanced exposure of an unexpected slip, an unexpected trip, an expected slip, and an expected trip using treadmill perturbations. Ankle joint kinematics for dorsiflexion and plantarflexion were quantified using three-dimensional (3D) motion capture through changes in ankle joint range of motion and using the SRS through changes in capacitance when stretched due to ankle movements...
Perception, planning, and control are three enabling technologies to achieve autonomy in autonomo... more Perception, planning, and control are three enabling technologies to achieve autonomy in autonomous driving. In particular, planning provides vehicles with a safe and collision-free path towards their destinations, accounting for vehicle dynamics, maneuvering capabilities in the presence of obstacles, traffic rules, and road boundaries. Existing path planning algorithms can be divided into two stages: global planning and local planning. In the global planning stage, global routes and the vehicle states are determined from a digital map and the localization system. In the local planning stage, a local path can be achieved based on a global route and surrounding information obtained from sensors such as cameras and LiDARs. In this paper, we present a new local path planning method, which incorporates a vehicle’s time-to-rollover model for off-road autonomous driving on different road profiles for a given predefined global route. The proposed local path planning algorithm uses a 3D occ...
2020 IEEE Frontiers in Education Conference (FIE), 2020
This Research Full Paper presents the approach of traditional engineering analysis techniques on ... more This Research Full Paper presents the approach of traditional engineering analysis techniques on education. Data mining techniques have been successfully employed to extract hidden information from large data sets within various contexts. We hypothesized that data mining techniques can similarly be applied to large educational data sets to extract and analyze patterns and create insights. Specifically, we examined the degree to which standard data mining techniques can distinguish between different student attention patterns in large lectures in which personal computers were actively used. Our data set consists of electronically captured student attention data (on-task, off-task) that was recorded at 20 second intervals throughout each course lecture over one semester. With Institutional Review Board (IRB) approval, methods involved capturing student data via a backend monitoring system to reduce student awareness of monitoring and reduce false behavior changes during data collection periods. The data were originally captured in the form of images (screenshots), and image processing techniques were applied to extract student attention patterns in the form of zero (off-task) and one (ontask). We conducted descriptive statistical analysis to add other features such as characterization information (e.g., total logged in attention, average class period attention to the recorded data sets). For the data mining analysis, we used three different supervised machine learning classification algorithms: Support Vector Machine (SVM), Decision Tree, and K-Nearest Neighbors (KNN) for classifying the students' dataset. We classified the students into one of four different classes based on their attention pattern in the lecture class. Before applying each classification algorithm, feature extraction was performed. For this purpose, we used Haar wavelets, Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA) dimensionality-reduction techniques before applying the classification algorithm. Their performance is compared. Our results indicate high classification accuracies can be obtained using these dimensional reduction algorithms followed by classification algorithms. Our result highlights the importance of applying traditional engineering analysis techniques to educational data in order to provide engineering education insights.
This paper examines target detection using a Linear Support Vector Machine (L-SVM). Traditional r... more This paper examines target detection using a Linear Support Vector Machine (L-SVM). Traditional radars typically use a Constant False Alarm Rate (CFAR) processor to adaptively adjust the detection threshold based on the fast-time return signal. The SVM formulation uses the same blockdiagram structure as the CFAR approach; however, data from the leading and lagging windows is directly used to classify each cell under test. The L-SVM method is compared to a Cell-Averaging CFAR (CA-CFAR) on simulated radar return signals with and without Swerling I targets. The results show that the L-SVM is able to detect very small SNR signals, while the CA-CFAR is unable to detect these signals below-10 dB SNR. In addition, the probability of detection and probability of false alarm for the L-SVM degrade much more gracefully than for the CA-CFAR detector for low-SNR targets.
When it comes to some essential abilities of autonomous ground vehicles (AGV), detection is one o... more When it comes to some essential abilities of autonomous ground vehicles (AGV), detection is one of them. In order to safely navigate through any known or unknown environment, AGV must be able to detect important elements on the path. Detection is applicable both on-road and off-road, but they are much different in each environment. The key elements of any environment that AGV must identify are the drivable pathway and whether there are any obstacles around it. Many works have been published focusing on different detection components in various ways. In this paper, a survey of the most recent advancements in AGV detection methods that are intended specifically for the off-road environment has been presented. For this, we divided the literature into three major groups: drivable ground and positive and negative obstacles. Each detection portion has been further divided into multiple categories based on the technology used, for example, single sensor-based, multiple sensor-based, and ho...
Fish species recognition is crucial to identifying the abundance of fish species in a specific ar... more Fish species recognition is crucial to identifying the abundance of fish species in a specific area, controlling production management, and monitoring the ecosystem, especially identifying the endangered species, which makes accurate fish species recognition essential. In this work, the fish species recognition problem is formulated as an object detection model to handle multiple fish in a single image, which is challenging to classify using a simple classification network. The proposed model consists of MobileNetv3-large and VGG16 backbone networks and an SSD detection head. Moreover, a class-aware loss function is proposed to solve the class imbalance problem of our dataset. The class-aware loss takes the number of instances in each species into account and gives more weight to those species with a smaller number of instances. This loss function can be applied to any classification or object detection task with an imbalanced dataset. The experimental result on the large-scale reef...
Standards for the fatigue testing of wearable sensing technologies are lacking. The majority of p... more Standards for the fatigue testing of wearable sensing technologies are lacking. The majority of published fatigue tests for wearable sensors are performed on proof-of-concept stretch sensors fabricated from a variety of materials. Due to their flexibility and stretchability, polymers are often used in the fabrication of wearable sensors. Other materials, including textiles, carbon nanotubes, graphene, and conductive metals or inks, may be used in conjunction with polymers to fabricate wearable sensors. Depending on the combination of the materials used, the fatigue behaviors of wearable sensors can vary. Additionally, fatigue testing methodologies for the sensors also vary, with most tests focusing only on the low-cycle fatigue (LCF) regime, and few sensors are cycled until failure or runout are achieved. Fatigue life predictions of wearable sensors are also lacking. These issues make direct comparisons of wearable sensors difficult. To facilitate direct comparisons of wearable sens...
An accurate and robust perception system is key to understanding the driving environment of auton... more An accurate and robust perception system is key to understanding the driving environment of autonomous driving and robots. Autonomous driving needs 3D information about objects, including the object’s location and pose, to understand the driving environment clearly. A camera sensor is widely used in autonomous driving because of its richness in color, texture, and low price. The major problem with the camera is the lack of 3D information, which is necessary to understand the 3D driving environment. Additionally, the object’s scale change and cclusion make 3D object detection more challenging. Many deep learning-based methods, such as depth estimation, have been developed to solve the lack of 3D information. This survey presents the image 3D object detection 3D bounding box encoding techniques, feature extraction techniques, and evaluation metrics of 3D object detection. The image-based methods are categorized based on the technique used to estimate an image’s depth information, and ...
Background: Wearable technology is used by clinicians and researchers and play a critical role in... more Background: Wearable technology is used by clinicians and researchers and play a critical role in biomechanical assessments and rehabilitation. Objective: The purpose of this research is to validate a soft robotic stretch (SRS) sensor embedded in a compression knee brace (smart knee brace) against a motion capture system focusing on knee joint kinematics. Methods: Sixteen participants donned the smart knee brace and completed three separate tasks: non-weight bearing knee flexion/extension, bodyweight air squats, and gait trials. Adjusted R2 for goodness of fit (R2), root mean square error (RMSE), and mean absolute error (MAE) between the SRS sensor and motion capture kinematic data for all three tasks were assessed. Results: For knee flexion/extension: R2 = 0.799, RMSE = 5.470, MAE = 4.560; for bodyweight air squats: R2 = 0.957, RMSE = 8.127, MAE = 6.870; and for gait trials: R2 = 0.565, RMSE = 9.190, MAE = 7.530 were observed. Conclusions: The smart knee brace demonstrated a higher...
IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018
Herein, we present a system for hyperspectral image segmentation that utilizes multiple class-bas... more Herein, we present a system for hyperspectral image segmentation that utilizes multiple class-based denoising autoencoders which are efficiently trained. Moreover, we present a novel hyperspectral data augmentation method for labelled HSI data using linear mixtures of pixels from each class, which helps the system with edge pixels which are almost always mixed pixels. Finally, we utilize a deep neural network and morphological hole-filling to provide robust image classification. Results run on the Salinas dataset verify the high performance of the proposed algorithm.
Opportunities to apply data mining techniques to analyze educational data and improve learning ar... more Opportunities to apply data mining techniques to analyze educational data and improve learning are increasing. A multitude of data are being produced by institutional technology, e-learning resources, and online and virtual courses. These data could be used by educators to analyze and understand the learning behaviors of students. The obtained data are raw data that must be analyzed, requiring educational data mining to predict useful information about students, such as academic performance, among other things. Many researchers have used traditional machine learning to predict the academic performance of students, and very little research has been conducted on the architecture of convolutional neural networks (CNNs) in the context of the pedagogical domain. We built a hybrid 2D CNN model by combining two different 2D CNN models to predict academic performance. Our sample comprised 1D data, so we transformed it to 2D image data to test the performance of our hybrid model. We compared...
2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2017
While the Choquet integral (ChI) is a powerful parametric nonlinear aggregation function, it has ... more While the Choquet integral (ChI) is a powerful parametric nonlinear aggregation function, it has limited scope and is not a universal function generator. Herein, we focus on a class of problems that are outside the scope of a single ChI. Namely, we are interested in tasks where different subsets of inputs require different ChIs. Herein, a genetic program (GP) is used to extend the ChI, referred to as GpChI hereafter, specifically in terms of compositions of ChIs and/or arithmetic combinations of ChIs. An algorithm is put forth to learn the different GP ChIs via genetic algorithm (GA) optimization. Synthetic experiments demonstrate GpChI in a controlled fashion, i.e., we know the answer and can compare what is learned to the truth. Real-world experiments are also provided for the mult-sensor fusion of electromagnetic induction (EMI) and ground penetrating radar (GPR) for explosive hazard detection. Our mutli-sensor fusion experiments show that there is utility in changing aggregation strategy per different subsets of inputs (sensors or algorithms) and fusing those results.
A deep-learning-based approach to estimating the number of coherent sources in radar is presented... more A deep-learning-based approach to estimating the number of coherent sources in radar is presented. A proper estimate of the number of sources in a signal enables improved angle-of-arrival (AoA) estimation common in applications such as radar, sonar, and communication systems. Many AoA estimators utilised in these areas require accurate estimates of the number of sources for enhanced performance. Herein, a robust method that performs well under the existence of coherent sources is developed. The proposed method is based on deep learning and it is shown to perform better than state-of-the-art versions of the Akaike Information Criteria (AIC), Minimum Description Length (MDL), and Exponentially Embedded Families (EEF) estimators, which employ spatial smoothing of the covariance matrix to handle coherent signals. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Autonomous Systems: Sensors, Processing, and Security for Vehicles and Infrastructure 2019, 2019
For autonomous vehicles 3D, rotating LiDAR sensors are often critically important towards the veh... more For autonomous vehicles 3D, rotating LiDAR sensors are often critically important towards the vehicle’s ability to sense its environment. Generally, these sensors scan their environment, using multiple laser beams to gather information about the range and the intensity of the reflection from an object. LiDAR capabilities have evolved such that some autonomous systems employ multiple rotating LiDARs to gather greater amounts of data regarding the vehicle’s surroundings. For these multi–LiDAR systems, the placement of the sensors determine the density of the combined point cloud. We perform preliminary research regarding the optimal LiDAR placement strategy on an off–road, autonomous vehicle known as the Halo project. We use the Mississippi State University Autonomous Vehicle Simulator (MAVS) to generate large amounts of labeled LiDAR data that can be used to train and evaluate a neural network used to process LiDAR data in the vehicle. The trained networks are evaluated and their performance metrics are then used to generalize the performance of the sensor pose. Data generation, training, and evaluation, was performed iteratively to perform a parametric analysis of the effectiveness of various LiDAR poses in the Multi–LiDAR system. We also, describe and evaluate intrinsic and extrinsic calibration methods that are applied in the multi–LiDAR system. In conclusion we found that our simulations are an effective way to evaluate the efficacy of various LiDAR placements based on the performance of the neural network used to process that data and the density of the point cloud in areas of interest.
M odern signal processing (SP) classes should provide a balance between theory and application as... more M odern signal processing (SP) classes should provide a balance between theory and application as well as use active learning exercises to engage students and facilitate learning. A new sensor processing course, Sensor Processing for Autonomous Vehicles (SPAV), was designed with two specific objectives: 1) to successfully engage students using active and collaborative learning and 2) integrate a state-of-the-art, physicsbased autonomy simulator into the class. The course was delivered to local and asynchronous distance students in spring 2020 at Mississippi State University (MSU). The MSU Autonomous Vehicle Simulator (MAVS) was used in the class. We also utilized three miniprojects to bring together theory and practice. We evaluated the course through student feedback. Results indicated that students viewed active exercises and the simulator as beneficial and useful, with multiple students describing those aspects as their favorite part of the course. Nearly all students (39 of 40) reported that they were engaged in the course.
This paper presents a retrospective of the benchmark testing methodologies developed and accumula... more This paper presents a retrospective of the benchmark testing methodologies developed and accumulated into the stretch sensor tool kit (SSTK) by the research team during the Closing the Wearable Gap series of studies. The techniques developed to validate stretchable soft robotic sensors (SRS) as a means for collecting human kinetic and kinematic data at the foot-ankle complex and at the wrist are reviewed. Lessons learned from past experiments are addressed, as well as what comprises the current SSTK based on what the researchers learned over the course of multiple studies. Three core components of the SSTK are featured: (a) material testing tools, (b) data analysis software, and (c) data collection devices. Results collected indicate that the stretch sensors are a viable means for predicting kinematic data based on the most recent gait analysis study conducted by the researchers (average root mean squared error or RMSE = 3.63°). With the aid of SSTK defined in this study summary and...
International Journal of Environmental Research and Public Health, 2020
Wearable sensors are beneficial for continuous health monitoring, movement analysis, rehabilitati... more Wearable sensors are beneficial for continuous health monitoring, movement analysis, rehabilitation, evaluation of human performance, and for fall detection. Wearable stretch sensors are increasingly being used for human movement monitoring. Additionally, falls are one of the leading causes of both fatal and nonfatal injuries in the workplace. The use of wearable technology in the workplace could be a successful solution for human movement monitoring and fall detection, especially for high fall-risk occupations. This paper provides an in-depth review of different wearable stretch sensors and summarizes the need for wearable technology in the field of ergonomics and the current wearable devices used for fall detection. Additionally, the paper proposes the use of soft-robotic-stretch (SRS) sensors for human movement monitoring and fall detection. This paper also recapitulates the findings of a series of five published manuscripts from ongoing research that are published as Parts I to ...
A novel wearable solution using soft robotic sensors (SRS) has been investigated to model foot-an... more A novel wearable solution using soft robotic sensors (SRS) has been investigated to model foot-ankle kinematics during gait cycles. The capacitance of SRS related to foot-ankle basic movements was quantified during the gait movements of 20 participants on a flat surface as well as a cross-sloped surface. In order to evaluate the power of SRS in modeling foot-ankle kinematics, three-dimensional (3D) motion capture data was also collected for analyzing gait movement. Three different approaches were employed to quantify the relationship between the SRS and the 3D motion capture system, including multivariable linear regression, an artificial neural network (ANN), and a time-series long short-term memory (LSTM) network. Models were compared based on the root mean squared error (RMSE) of the prediction of the joint angle of the foot in the sagittal and frontal plane, collected from the motion capture system. There was not a significant difference between the error rates of the three diff...
The purpose of this study was to use 3D motion capture and stretchable soft robotic sensors (SRS)... more The purpose of this study was to use 3D motion capture and stretchable soft robotic sensors (SRS) to collect foot-ankle movement on participants performing walking gait cycles on flat and sloped surfaces. The primary aim was to assess differences between 3D motion capture and a new SRS-based wearable solution. Given the complex nature of using a linear solution to accurately quantify the movement of triaxial joints during a dynamic gait movement, 20 participants performing multiple walking trials were measured. The participant gait data was then upscaled (for the SRS), time-aligned (based on right heel strikes), and smoothed using filtering methods. A multivariate linear model was developed to assess goodness-of-fit based on mean absolute error (MAE; 1.54), root mean square error (RMSE; 1.96), and absolute R2 (R2; 0.854). Two and three SRS combinations were evaluated to determine if similar fit scores could be achieved using fewer sensors. Inversion (based on MAE and RMSE) and plant...
Background: An induced loss of balance resulting from a postural perturbation has been reported a... more Background: An induced loss of balance resulting from a postural perturbation has been reported as the primary source for postural instability leading to falls. Hence; early detection of postural instability with novel wearable sensor-based measures may aid in reducing falls and fall-related injuries. The purpose of the study was to validate the use of a stretchable soft robotic sensor (SRS) to detect ankle joint kinematics during both unexpected and expected slip and trip perturbations. Methods: Ten participants (age: 23.7 ± 3.13 years; height: 170.47 ± 8.21 cm; mass: 82.86 ± 23.4 kg) experienced a counterbalanced exposure of an unexpected slip, an unexpected trip, an expected slip, and an expected trip using treadmill perturbations. Ankle joint kinematics for dorsiflexion and plantarflexion were quantified using three-dimensional (3D) motion capture through changes in ankle joint range of motion and using the SRS through changes in capacitance when stretched due to ankle movements...
Perception, planning, and control are three enabling technologies to achieve autonomy in autonomo... more Perception, planning, and control are three enabling technologies to achieve autonomy in autonomous driving. In particular, planning provides vehicles with a safe and collision-free path towards their destinations, accounting for vehicle dynamics, maneuvering capabilities in the presence of obstacles, traffic rules, and road boundaries. Existing path planning algorithms can be divided into two stages: global planning and local planning. In the global planning stage, global routes and the vehicle states are determined from a digital map and the localization system. In the local planning stage, a local path can be achieved based on a global route and surrounding information obtained from sensors such as cameras and LiDARs. In this paper, we present a new local path planning method, which incorporates a vehicle’s time-to-rollover model for off-road autonomous driving on different road profiles for a given predefined global route. The proposed local path planning algorithm uses a 3D occ...
Uploads
Papers by John E Ball