Abstract
Order picking has driven an increase in the number of logistics researchers. Robotics can help reduce the operational cost of such a process, eliminating the need for a human operator to perform trivial and dangerous tasks such as moving around the warehouse. However, for a mobile robot to perform such tasks, certain problems, such as defining the best path, must be solved. Among the most prominent techniques applied in the calculation of the trajectories of these robotic agents are potential fields and the A* algorithm. However, these techniques have limitations. This study aims to demonstrate a new approach based on the behavior of oceanic relief to map an environment that simulates a logistics warehouse, considering distance, safety, and efficiency in trajectory planning. In this manner, we seek to solve some of the limitations of traditional algorithms. We propose a new mapping technique for mobile robots, followed by a new trajectory planning approach.

Abstract
Artificial intelligence (AI) is playing a growing role today in several areas, especially in health, where understanding AI models and their predictions is extremely important for health professionals. In this context, Explainable AI (XAI) plays a crucial role in seeking to provide understandable explanations for these models. This article analyzes two different XAI approaches applied to analyzing gastric endoscopy images. The first, more conventional approach uses Grad CAM, while the second, even less explored but with great potential, is based on similarity-based explanations. This example-based XAI technique aims to provide representative examples to support the decisions of AI models. In this study, we compare these two techniques applied to two different models: one based on the VGG16 architecture and the other based on ResNet50, designed to classify images from the KVASIR-capsule database. The results reveal that Grad-CAM provided intuitive explanations only for the VGG16 model, while the similarity-based explanations technique provided consistent explanations for both models. We conclude that exploring other XAI techniques can be a significant asset in improving the understanding of the various AI models.

Abstract
Soil contamination with metals is a major threat for the environment and public health since most metals are toxic to humans and to non-human biota, even at low concentrations. Thus, new sustainable remediation approaches are currently needed to immobilize metals in soils to decrease their mobility and bioavailability. In this work, we explore the application of discarded substrates from hydroponic cultivation, namely coconut shell and a mixture of coconut shell and pine bark, for immobilization of metals (Cd, Cr, Ni, Cu, Pb, Hg, Sb and As) in a naturally contaminated soil from a mining region in Portugal. The immobilization capacity of substrates (added to the soil at 5% mass ratio) was assessed both individually and also combined with other traditional agriculture soil additives (limestone and gypsum, at 2% mass ratio) and nanoparticles of zero-valent iron (nZVI) at 1–3% mass ratio. The overall results obtained after a 30-d incubation showed that the discarded substrates are a viable, economic, and environmental-friendly solution for metal remediation in soils, with the capacity of immobilization ranging from 20 to 91% for the metals and metalloids studied. Furthermore, they showed the capacity to reduce the soil toxicity (EC50 ~ 6000 mg/L) to non-toxic levels (EC50 > 10000 mg/L) to the bacteria Aliivrio fischeri. © 2024 The Authors

Abstract
Cooperative robotics is exponentially gaining strength in scientific research, especially regarding the cooperation between ground mobile robots and Unmanned Aerial Vehicles (UAVs), where the remaining challenges are equipollent to its potential uses in different fields, such as agriculture and electrical tower inspections. Due to the complexity involved in the process, precision landing by UAVs on moving robotic platforms for tasks such as battery hot-swapping is a major open research question. This work explores the feasibility and accuracy of different fiducial markers to aid in the precision landing process by a UAV on a mobile robotic platform. For this purpose, a TelloUAV was used to acquire images at different positions, angles, and distances from ArUco, ARTag, and ArUco Board markers to evaluate their detection precision. The analyses demonstrate the highest reliability in the measurements performed through the ArUco marker. Future work will be devoted to using the ArUco marker to perform precision landing on a mobile robotic platform, considering the necessary adjustments to lessen the impact of errors intrinsic to detecting the fiducial marker during the landing procedure.

Abstract
The application of optical fibers in optogenetics is rapidly expanding due to their compactness, cost-effectiveness, sensitivity, and accuracy. This paper introduces a twin-core optical fiber (TCF) sensor employing a Mach-Zehnder interferometer (MZI) to monitor the optogenetic response of opsin-expressing human dental pulp stem cells (hDPSCs) based on refractive index (RI) measuring. In order to improve the RI sensitivity of the sensor, an in fiber Mach-Zeander modulator formed using TCF optics segments can detect changes in the RI in the surrounding medium, and in order to improve the RI sensitivity of the sensor, it is proposed to etch one side of the TCF cladding. The RI sensitivity of the sensor was obtained 233.62 nm/RIU in the range of 1.33-1.4 RIU and 870.01 nm/RIU in the range of 1.4-1.43 RIU, R2 = 0.99. simulation results show that in terms of sensor sensitivity and spectral response, there is a good agreement between the theoretical and experimental results, indicating that the TCF-MZI sensor can perform optical neural recording. In vitro experiments monitored wavelength changes in opsin-expressing and non-opsin-expressing in human dental pulp stem cells (hDPSCs) during optogenetic stimulation with 473 nm pulsed illumination. The results revealed that optical stimulation of ChR2 opsin-expressing hDPSCs leads to active the light sensitive ion channel and changing the effective RI of the surrounding medium. The neural activity is driven by changes in intracellular and extracellular ion concentrations, which lead to alterations in the RI of the cell medium RI variations detectable by the sensor. The novel sensor structure demonstrated its ability to detect RI changes in the cell medium during optogenetic stimulation and fiber optic sensors can be a good candidate for optical recording of the neural activity. Beyond these in vivo applications, label free fiber optic biosensors-based IR measurement can be used for all optical multifunctional probe in stimulation, recording, and sensing of neuroscience applications.

Abstract
Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns. Using a population- based approach, our approach utilizes distributional anomaly detection. This method diverges from traditional instance-wise approaches by focusing on sets of scans instead of individual images. Using an autoencoder to extract feature representations, we present instance-based and distribution-based assessments of the separability between COVID-positive and COVIDnegative pneumonia radiographs. The results demonstrate that the proposed distribution-based methodology outperforms conventional instance-based techniques in identifying radiographic changes associated with COVID-positive cases. This underscores its potential as an early warning system capable of detecting significant distributional shifts in radiographic data. By continuously monitoring these changes, this approach offers a mechanism for early identification of emerging health trends, potentially signaling the onset of new pandemics and enabling prompt public health responses.