Digital In Situ Data Collection in Earth Observation, Monitoring and Agriculture—Progress towards Digital Agriculture

Digital solutions in agricultural management promote food security and support the sustainable use of resources. As a result, remote sensing (RS) can be seen as an innovation for the fast generation of reliable information for agricultural management. Near real-time processed RS data can be used as a tool for decision making on multiple scales, from subplot to the global level. This high potential is not yet fully applied, due to often limited access to ground truth information, which is crucial for the development of transferable applications and acceptance. In this study we present a digital workflow for the acquisition, processing and dissemination of agroecological information based on proprietary and open-source software tools with state-of-the-art web-mapping technologies. Data is processed in near real-time and thus can be used as ground truth information to enhance quality and performance of RS-based products. Data is disseminated by easy-to-understand visualizations and download functionalities for specific application levels to serve specific user needs. It thus can increase expert knowledge and can be used for decision support at the same time. The fully digital workflow underpins the great potential to facilitate quality enhancement of future RS products in the context of precision agriculture by safeguarding data quality. The generated FAIR (findable, accessible, interoperable, reusable) datasets can be used to strengthen the relationship between scientists, initiatives and stakeholders.

BYANJON: A Ground Truth Preparation System for Online Handwritten Bangla Documents

The work reported in this article deals with the ground truth generation scheme for online handwritten Bangla documents at text-line, word, and stroke levels. The aim of the proposed scheme is twofold: firstly, to build a document level database so that future researchers can use the database to do research in this field. Secondly, the ground truth information will help other researchers to evaluate the performance of their algorithms developed for text-line extraction, word extraction, word segmentation, stroke recognition, and word recognition. The reported ground truth generation scheme starts with text-line extraction from the online handwritten Bangla documents, then words extraction from the text-lines, and finally segmentation of those words into basic strokes. After word segmentation, the basic strokes are assigned appropriate class labels by using modified distance-based feature extraction procedure and the MLP ( Multi-layer Perceptron ) classifier. The Unicode for the words are then generated from the sequence of stroke labels. XML files are used to store the stroke, word, and text-line levels ground truth information for the corresponding documents. The proposed system is semi-automatic and each step such as text-line extraction, word extraction, word segmentation, and stroke recognition has been implemented by using different algorithms. Thus, the proposed ground truth generation procedure minimizes huge manual intervention by reducing the number of mouse clicks required to extract text-lines, words from the document, and segment the words into basic strokes. The integrated stroke recognition module also helps to minimize the manual labor needed to assign appropriate stroke labels. The freely available and can be accessed at https://byanjon.herokuapp.com/ .

A simple machine learning based framework for processing the inline inspection data of subsea pipelines

This paper presents a simple machine learning based framework for diagnosing the inline inspection data (ILI) of subsea pipelines. ILI data are obtained by intelligent pigging devices operating along subsea pipelines. The wall thickness (WT) and standoff distance (SO) are collected by the sensors installed on the pigging, which are normally in the format of 2D arrays. There are many uncertainties for the ILI data collected from the offshore survey. An attempt was made to apply the machine learning method to diagnose the uncertainties. A convolutional neural network (CNN) is used, the ILI data are discretized and processed in 64x64 grid size. Fabricated training datasets were made for training the machine learning model since the ground truth information (actual corroded wall thickness) is hardly known in this case. The trained model was successfully. It is demonstrated that certain corrosion patterns have been recognized by the trained model. Comparisons were performed between the new method and traditional methods with case studies on real ILI data. The validity of the methodology was discussed.

Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment

Learning how to execute complex tasks involving multiple objects in a 3D world is challenging when there is no ground-truth information about the objects or any demonstration to learn from. When an agent only receives a signal from task-completion, this makes it challenging to learn the object-representations which support learning the correct object-interactions needed to complete the task. In this work, we formulate learning an attentive object dynamics model as a classification problem, using random object-images to define incorrect labels for our object-dynamics model. We show empirically that this enables object-representation learning that captures an object's category (is it a toaster?), its properties (is it on?), and object-relations (is something inside of it?). With this, our core learner (a relational RL agent) receives the dense training signal it needs to rapidly learn object-interaction tasks. We demonstrate results in the 3D AI2Thor simulated kitchen environment with a range of challenging food preparation tasks. We compare our method's performance to several related approaches and against the performance of an oracle: an agent that is supplied with ground-truth information about objects in the scene. We find that our agent achieves performance closest to the oracle in terms of both learning speed and maximum success rate.

Registered report protocol: Developing an artifact index for capacitive electrocardiography signals acquired with an armchair

Continuous monitoring of an electrocardiogram (ECG) in private diagnostic spaces such as vehicles or apartments allows early detection of cardiovascular diseases. We will use an armchair with integrated capacitive electrodes to record the capacitive electrocardiogram (cECG) during everyday activities. However, movements and other artifacts affect the signal quality. Therefore, an artifact index is needed to detect artifacts and classify the cECG. The unavailability of cECG data and reliable ground truth information requires new recordings to develop an artifact index. This study is designed to test the hypothesis: an artifact index can be devised, which intends to estimate the signal quality of segments and classify signals. In a single-arm study with 44 subjects, we will record two activities of 11-minute duration: reading and watching television. During recording, we will capture cECG, ECG, and oxygen saturation (SpO2) with time synchronization as well as keypoint-based movement indicators obtained from a video camera. SpO2 provides additional information on the subject’s health status. The keypoint-based movements indicate artifacts in the cECG. We will combine all ground truth data to evaluate the index. In the future, we aim at using the artifact index to exclude cECG segments with artifacts from further analysis. This will improve cECG technology for the measurement of cardiovascular parameters.

Visual analysis of density and velocity profiles in dense 3D granular gases

Granular multiparticle ensembles are of interest from fundamental statistical viewpoints as well as for the understanding of collective processes in industry and in nature. Extraction of physical data from optical observations of three-dimensional (3D) granular ensembles poses considerable problems. Particle-based tracking is possible only at low volume fractions, not in clusters. We apply shadow-based and feature-tracking methods to analyze the dynamics of granular gases in a container with vibrating side walls under microgravity. In order to validate the reliability of these optical analysis methods, we perform numerical simulations of ensembles similar to the experiment. The simulation output is graphically rendered to mimic the experimentally obtained images. We validate the output of the optical analysis methods on the basis of this ground truth information. This approach provides insight in two interconnected problems: the confirmation of the accuracy of the simulations and the test of the applicability of the visual analysis. The proposed approach can be used for further investigations of dynamical properties of such media, including the granular Leidenfrost effect, granular cooling, and gas-clustering transitions.

A Data-Driven Travel Mode Share Estimation Framework based on Mobile Device Location Data

Mobile device location data (MDLD) contains abundant travel behavior information to support travel demand analysis. Compared to traditional travel surveys, MDLD has larger spatiotemporal coverage of the population and its mobility. However, ground truth information such as trip origins and destinations, travel modes, and trip purposes are not included by default. Such important attributes must be imputed to maximize the usefulness of the data. This paper targets at studying the capability of MDLD on estimating travel mode share at aggregated levels. A data-driven framework is proposed to extract travel behavior information from MDLD. The proposed framework first identifies trip ends with a modified Spatiotemporal Density-based Spatial Clustering of Applications with Noise (ST-DBSCAN) algorithm. Then three types of features are extracted for each trip to impute travel modes using machine learning models. A labeled MDLD dataset with ground truth information is used to train the proposed models, resulting in a 95% recall rate in identifying trip ends and a 93% 10-fold cross-validation accuracy in imputing the five travel modes (drive, rail, bus, bike and walk) with a Random Forest (RF) classifier. The proposed framework is then applied to two large-scale MDLD datasets, covering the Baltimore-Washington metropolitan area and the United States, respectively. The estimated trip distance, trip time, trip rate distribution, and travel mode share are compared against travel surveys at different geographies. The results suggest that the proposed framework can be readily applied in different states and metropolitan regions with low cost in order to study multimodal travel demand, understand mobility trends, and support decision making.

Performance Evaluation of the Highway Radar Occupancy Grid

The quality of environmental perception is crucial for automated vehicle capabilities. In order to ensure the required accuracy, the occupancy grid mapping algorithm is often utilised to fuse data from multiple sensors. This paper focuses on the radar-based occupancy grid for highway applications and describes how to measure effectively the quality of the occupancy map. The evaluation was performed using the novel grid pole-like object analysis method. The proposed assessment is versatile and can be applied without detailed ground truth information. The evaluation was tested with a simulation and real vehicle experiments on the highway.

Outliers in Smartphone Sensor Data Reveal Outliers in Daily Happiness

Enabling smartphones to understand our emotional well-being provides the potential to create personalised applications and highly responsive interfaces. However, this is by no means a trivial task - subjectivity in reporting emotions impacts the reliability of ground-truth information whereas smartphones, unlike specialised wearables, have limited sensing capabilities. In this paper, we propose a new approach that advances emotional state prediction by extracting outlier-based features and by mitigating the subjectivity in capturing ground-truth information. We utilised this approach in a distinctive and challenging use case - happiness detection - and we demonstrated prediction performance improvements of up to 13% in AUC and 27% in F-score compared to the traditional modelling approaches. The results indicate that extreme values (i.e. outliers) of sensor readings mirror extreme values in the reported happiness levels. Furthermore, we showed that this approach is more robust in replicating the prediction model in completely new experimental settings.