Automatic Fungi Recognition: Deep Learning Meets Mycology

The article presents an AI-based fungi species recognition system for a citizen-science community. The system’s real-time identification too — FungiVision — with a mobile application front-end, led to increased public interest in fungi, quadrupling the number of citizens collecting data. FungiVision, deployed with a human-in-the-loop, reaches nearly 93% accuracy. Using the collected data, we developed a novel fine-grained classification dataset — Danish Fungi 2020 (DF20) — with several unique characteristics: species-level labels, a small number of errors, and rich observation metadata. The dataset enables the testing of the ability to improve classification using metadata, e.g., time, location, habitat and substrate, facilitates classifier calibration testing and finally allows the study of the impact of the device settings on the classification performance. The continual flow of labelled data supports improvements of the online recognition system. Finally, we present a novel method for the fungi recognition service, based on a Vision Transformer architecture. Trained on DF20 and exploiting available metadata, it achieves a recognition error that is 46.75% lower than the current system. By providing a stream of labeled data in one direction, and an accuracy increase in the other, the collaboration creates a virtuous cycle helping both communities.

Improving Walking Economy With an Ankle Exoskeleton Prior to Human-in-the-Loop Optimization

Lower limb robotic exoskeletons have shown the capability to enhance human locomotion for healthy individuals or to assist motion rehabilitation and daily activities for patients. Recent advances in human-in-the-loop optimization that allowed for assistance customization have demonstrated great potential for performance improvement of exoskeletons. In the optimization process, subjects need to experience multiple types of assistance patterns, thus, leading to a long evaluation time. Besides, some patterns may be uncomfortable for the wearers, thereby resulting in unpleasant optimization experiences and inaccurate outcomes. In this study, we investigated the effectiveness of a series of ankle exoskeleton assistance patterns on improving walking economy prior to optimization. We conducted experiments to systematically evaluate the wearers' biomechanical and physiological responses to different assistance patterns on a lightweight cable-driven ankle exoskeleton during walking. We designed nine patterns in the optimization parameters range which varied peak torque magnitude and peak torque timing independently. Results showed that metabolic cost of walking was reduced by 17.1 ± 7.6% under one assistance pattern. Meanwhile, soleus (SOL) muscle activity was reduced by 40.9 ± 19.8% with that pattern. Exoskeleton assistance changed maximum ankle dorsiflexion and plantarflexion angle and reduced biological ankle moment. Assistance pattern with 48% peak torque timing and 0.75 N·m·kg−1 peak torque magnitude was effective in improving walking economy and can be selected as an initial pattern in the optimization procedure. Our results provided a preliminary understanding of how humans respond to different assistances and can be used to guide the initial assistance pattern selection in the optimization.

An Articulated Robotic Forceps Design with a Parallel Wrist-Gripper Mechanism and Parasitic Motion Compensation

In this paper, a novel 4 degrees-of-freedom articulated parallel forceps mechanism with a large orientation workspace (±/−90deg in pitch and yaw, 360deg in roll rotations) is presented for robotic minimally invasive surgery. The proposed 3RSR-1UUP parallel mechanism utilizes a UUP center-leg which can convert thrust motion of the 3RSR mechanism into gripping motion. This design eliminates the need for an additional gripper actuator, but also introduces the problem of unintentional gripper opening/closing due to parasitic motion of the 3RSR mechanism. Here, position kinematics of the proposed mechanism, including the workspace, is analyzed in detail, and a solution to the parasitic motion problem is provided. Human in the loop simulations with a haptic interface are also performed to confirm the feasibility of the proposed design.

Interactive Deep Learning for Shelf Life Prediction of Muskmelons Based on an Active Learning Approach

A pivotal topic in agriculture and food monitoring is the assessment of the quality and ripeness of agricultural products by using non-destructive testing techniques. Acoustic testing offers a rapid in situ analysis of the state of the agricultural good, obtaining global information of its interior. While deep learning (DL) methods have outperformed state-of-the-art benchmarks in various applications, the reason for lacking adaptation of DL algorithms such as convolutional neural networks (CNNs) can be traced back to its high data inefficiency and the absence of annotated data. Active learning is a framework that has been heavily used in machine learning when the labelled instances are scarce or cumbersome to obtain. This is specifically of interest when the DL algorithm is highly uncertain about the label of an instance. By allowing the human-in-the-loop for guidance, a continuous improvement of the DL algorithm based on a sample efficient manner can be obtained. This paper seeks to study the applicability of active learning when grading ‘Galia’ muskmelons based on its shelf life. We propose k-Determinantal Point Processes (k-DPP), which is a purely diversity-based method that allows to take influence on the exploration within the feature space based on the chosen subset k. While getting coequal results to uncertainty-based approaches when k is large, we simultaneously obtain a better exploration of the data distribution. While the implementation based on eigendecomposition takes up a runtime of O(n3), this can further be reduced to O(n·poly(k)) based on rejection sampling. We suggest the use of diversity-based acquisition when only a few labelled samples are available, allowing for better exploration while counteracting the disadvantage of missing the training objective in uncertainty-based methods following a greedy fashion.

Sensing and Human Factors Research: A Review

Human experts are integral to the success of computational earth observation. They perform various visual decision-making tasks, from selecting data and training machine-learning algorithms to interpreting accuracy and credibility. Research concerning the various human factors which affect performance has a long history within the fields of earth observation and the military. Shifts in the analytical environment from analog to digital workspaces necessitate continued research, focusing on human-in-the-loop processing. This article reviews the history of human-factors research within the field of remote sensing and suggests a framework for refocusing the discipline's efforts to understand the role that humans play in earth observation.