Remote vibrometry vehicle classification

Background: Detecting manifestations of spatial disorientation in real time is a key requirement for adaptive assistive navigation systems for people with dementia. Objective: To identify predictive patterns of spatial disorientation in cognitively impaired people during unconstrained locomotion behavior in an urban environment. Methods: Accelerometric data and GPS records were gathered during a wayfinding task along a route of about 1 km in 15 people with amnestic mild cognitive impairment or clinically probable Alzheimer’s disease dementia (13 completers). We calculated a set of 48 statistical features for each 10-s segment of the acceleration sensor signal to characterize the physical motion. We used different classifiers with the wrapper method and leave-one-out cross-validation for feature selection and for determining accuracy of disorientation detection. Results: Linear discriminant analysis using three features showed the best classification results, with a cross-validated ROC AUC of 0.75, detecting 65% of all scenes of spatial disorientation in real time. Consideration of an additional feature that informed about a person’s distance to the next traffic junction did not provide an additional information gain. Conclusions: Accelerometric data are able to capture the uniformity and activity of a person’s walking, which are identified as the most informative locomotion features of spatially disoriented behavior. This serves as an important basis for real-time navigation assistance. To improve the required accuracy of real-time disorientation prediction, as a next step we will analyze whether location-based behavior is able to inform about person-centered habitual factors of orientation.

Assessing the effects of sampling frequency on behavioural classification of accelerometer data

Embedded with a wide variety of sensors, such as GPSs, accelerometers, gyroscopes, and microphones, smartphones have become a very useful tool in the context of travel surveys. In this chapter, the authors present an innovative tool to estimate individuals' mobility patterns using an application for smartphones that records GPS and accelerometer data from trips annotated by the user. The authors also present a neural network model for the classification of trips into four transportation modes, based on features extracted from the accelerometer signal. A small sample was collected in Valencia (Spain) to train and evaluate the model. The best classification results were achieved for detecting walking trips (98.2%) and bike rides (99.3%).

A Strategy on How to Utilize Smartphones for Automatically Reconstructing Trips in Travel Surveys

For canid species, scent marking plays a critical role in territoriality, social dynamics, and reproduction. However, due in part to human dependence on vision as our primary sensory modality, research on olfactory communication is hampered by a lack of tractable methods. In this study, we leverage a powerful biologging approach, using accelerometers in concert with GPS loggers to monitor and describe scent-marking events in time and space. We performed a validation experiment with domestic dogs, monitoring them by video concurrently with the novel biologging approach. We attached an accelerometer to the pelvis of 31 dogs (19 males and 12 females), detecting raised-leg and squat posture urinations by monitoring the change in device orientation. We then deployed this technique to describe the scent marking activity of 3 guardian dogs as they defend livestock from coyote depredation in California, providing an example use-case for the technique. During validation, the algorithm correctly classified 92% of accelerometer readings. High performance was partly due to the conspicuous signatures of archetypal raised-leg postures in the accelerometer data. Accuracy did not vary with the weight, age, and sex of the dogs, resulting in a method that is broadly applicable across canid species’ morphologies. We also used models trained on each individual to detect scent marking of others to emulate the use of captive surrogates for model training. We observed no relationship between the similarity in body weight between the dog pairs and the overall accuracy of predictions, although models performed best when trained and tested on the same individual. We discuss how existing methods in the field of movement ecology can be extended to use this exciting new data type. This paper represents an important first step in opening new avenues of research by leveraging the power of modern-technologies and machine-learning to this field.

Involuntary movements of arms and legs reflect neural and metabolic processes in the human body. In this paper the focus is on the properties of physiological tremor, shivering, and tremors caused by physical fatigue measured in fingers of a subject. Three different signal modeling paradigms are compared in the paper using accelerometer data. It is first demonstrated that the data can be modeled as a nearly stationary low-order AR process. Next, it is shown that the different data types can be classified using long-term feature distributions in a naive Bayes classifier. Finally, a comparable performance is obtained when the signal is modeled as a Markov process emitting small prototypical movements or jerks.

In this paper, an empirical evaluation of different classification techniques is conducted on user movement data. The datasets used here for experiments are composed of accelerometer data collected from various devices, including smartphones and smart watches. The user movement data was processed and fed into five traditional machine learning algorithms. The classification performances were then compared with a deep learning technique, the Long Short Term Memory-Recurrent Neural Network (LSTM-RNN). LSTM-RNN achieved its highest accuracy at 89% as opposed to 97% from a traditional machine learning algorithm, specifically, K-Nearest Neighbors (k-NN), on wrist-worn accelerometer data.

Space frames are usually used to enhance structural strength of the vehicle while reducing its overall mass. These frames are comprised of beams that are joined together. Recently, space frames are being incorporated in military vehicles. Space frames in military vehicles are however subjected to different types of loading than what is encountered in civilian vehicles such as projectile impacts and land mine blasts. Due to the need to replace a damaged section of the space frame quickly, the proposed space frame is composed of hollow square cross-section bars and angle sections that are bolted together. The space frame is enclosed by uniform-thickness armor, except at the turret. The vehicle is subjected to high impact load to simulate a projectile hit. The objective of this work is to minimize shocks at various critical locations of the space frame while maintaining the overall structural integrity of the vehicle. The vehicle model is parameterized to achieve this objective. This problem is solved using the Successive Heuristic Quadratic Approximation (SHQA) technique, which combines successive quadratic approximation with an adaptive random search within varying search space. The entire optimization process is carried out within MATLAB environment.

We have designed an augmented reality (AR) game for children with cerebral palsy (CP) to perform home-based neurorehabilitation. A Myo armband detects electromyographic (EMG) signals and accelerometer data from the arm, and a trained classifier determines whether the neuromotor performance of the arm satisfies the expectation of the exercise. The user can move a virtual object only through therapist-prescribed motor movement. The user completes the exercise by moving the virtual object to some targets displayed in the glass.

In this paper, we present one of the winning solutions of an international human activity recognition challenge organized by DrivenData in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. The objective of the challenge was to predict activities of daily living and posture or ambulation based on wrist-worn accelerometer, RGB-D camera, and passive environmental sensor data, which was collected from a smart home in the UK. Most of the state of the art research focus on one type of data, e.g., wearable sensor data, for making predictions and overlook the usefulness of user locations for this purpose. In our work, we propose a novel approach that leverages heterogeneous data types as well as user locations for building predictive models. Note that while we do not have actual location information but we build models to predict location using machine learning models and use the predictions in user activity recognition. Compared to the state of the art, our proposed approach is able to achieve a 38% improvement with a Brier score of 0.1346. This means that roughly 9 out of 10 predictions matched the human-labeled descriptions.

This paper presents a two-phase design for the classification of the human movement activities of running, walking and standing by using accelerometer data logged from smartphone. The first phase of the design is, the two-stage filter applied for the process of raw acceleration data collected from the accelerometer; and the second phase of the design is, the classification of human movements using Logistic Regression with Gradient Descent Algorithm as classifier from the clean data produced by first phase of the design. The raw acceleration data from the tri-axial accelerometer of smartphone contains three axes accelerations. This acceleration data are collected separately for each movement activity and are used for the training and testing of design by using a simulation environment. The activity classification results are promising and show that the proposed design provides an overall accuracy of more than 97% on both train data and the separate independent test data for the classification of human movement activities of running, walking and standing.

GPS and accelerometer tracking presently revolutionises the fields of ecology and animal behaviour. However, the effects of tag characteristics like weight, attachment and data quality on study outcomes and animal welfare are important to consider. In this study, we compare how different tag attachment types influence the behaviour of a group of tagged large waterbirds, GPS accuracy and behaviour classification success from accelerometer data. Both neckband and backpack tags had similar effects on the behaviour of six captive Canada geese (Branta canadensis), increasing the amount of discomfort behaviour in relation to untagged individuals. Both treatment groups also slightly decreased the amount of foraging, but the duration of neither vigilance nor resting was affected. GPS positions that were filtered with classical GPS platform settings (i.e. smoothing) were more accurate than positions improved by satellite-based differential augmentation. Tag attachment, however, did not induce any differences in position accuracy of both data types. Behaviour classification success was generally similar for neckband and backpack tags. But in detail, behaviours mainly performed by the head like foraging and vigilance were better detected from accelerometer data of neckband tags, whereas behaviours like resting and walking were more successfully detected from backpack tag data. Our findings suggest that the use of neckband or backpack tags for tracking large waterbirds and their behaviour largely depends on which behaviours are most important to detect. However, for wildlife tracking studies, factors like tag retention time are also of great importance, especially for animals like some goose species that are known to quickly destroy backpack tags. For future studies, we advise to carefully evaluate not only tag weight, but also attachment methods and data quality, because the right choice depends on the research question. This will improve the scope of wildlife tracking even more for various scientific, conservation and management applications.

Falls are one of the leading factors of injury and fatality in older adults. Given the importance of early detection of adults at higher risk of falls, we evaluated the ability of machine learning to classify fall risk in adults across the lifespan using wearable sensors embedded in a smartshirt. We evaluated the classification performance of binary and multiclass fall risk classifier models using SciKit Digital Health in adults across the lifespan. Using a k-fold and group k-fold cross-validation strategy, we demonstrate the feasibility of fall risk classification using accelerometer data from 10 second epochs of treadmill walking data from adults across the lifespan. We achieved an 88% accuracy in a binary clasifier of fallers vs. non-fallers, and an 86% accuracy in a multiclass classifier comparing non-fallers, fallers, and recurrent fallers using retrospective fall histories. Comparing group k-fold vs. k-fold cross-validation strategies, we find a 22-27% drop-off in accuracy performance. Furthering the evaluation framework presented in this study would be valuable to the development of more robust and clinically relevant models used in the prediction of fall risk. These models could one day be applied in clinical settings to help better diagnose and monitor fall risk among older adults, improving the care of at-risk individuals and reducing the injury and associated cost of falls.

The effect of data sources and quality on the predictive capacity of CLIMEX models: An assessment of Teleonemia scrupulosa and Octotoma scabripennis for the biocontrol of Lantana camara in Australia

COVID‐19 has had a profound global impact, necessitating the development of infection detection systems based on machine learning. This paper presents a Multi‐task architecture that addresses the classification and segmentation tasks for COVID‐19 detection. The model comprises an encoder for feature representation, a decoder for segmentation, and a multi‐layer perceptron for classification. Evaluations conducted on two datasets demonstrate the model's performance in both classification and segmentation. To enhance efficiency and diagnosis accuracy, CT‐scan images undergo pre‐processing using image processing algorithms like histogram equalization, median filtering, and mathematical morphology operations. The combination of the median filter pre‐processing and the proposed model yields impressive results in the classification task, achieving high accuracy, sensitivity, and specificity, with values of 0.97, 0.97, and 0.96, respectively, for dataset 1, and 0.96 in mentioned metrics for dataset 2. For segmentation, the proposed model, particularly with the average morphology pre‐processing, exhibits excellent performance with high accuracy, low mean squared error, high peak signal‐to‐noise ratio, high structural similarity index, and a mean dice coefficient of 88.86 ± 0.05 for dataset 1, and 87.97 ± 0.02 for dataset 2. Furthermore, the pre‐trained models consistently demonstrate the superiority of the median filter and proposed model in the classification task on the same datasets. In conclusion, the proposed multi‐task model, incorporating image processing techniques, achieves remarkable results in both classification and segmentation. The utilization of pre‐processing algorithms and the multi‐task framework significantly contribute to superior performance metrics. This study encourages further exploration of combining diverse image processing algorithms to advance infection diagnosis and treatment.