In order to optimize the movements of a robot, every object found in the work environment must not just be identified, but located in reference to the robot itself. Usually, object segmentation from an image is achieved using color segmentation. This segmentation can be achieved by processing the R, G and B chromatic components. However, this method has the disadvantage of been very sensitive to the changes on lighting. Converting the RGB image to the CIE-Lab color space avoids the lack of sensitivity by increasing the accuracy of the color segmentation. Unfortunately, if multiple objects of the same color are presented in the scene, is not possible to identify one of these objects using only this color space. Therefore, we need to consider an additional data source, in this case the depth, in order to discriminate objects that are not in the same plane as the object of interest. In this paper, we introduce an algorithm to detect objects, essentially on indoor environments, using CIE-Lab and depth segmentation techniques. We process the color and depth images provided by the Kinect sensor for proposing a visual strategy with real-time performanc

Despite the increasing use of technology, handwriting has remained to date as an efficient means of communication. Certainly, handwriting is a critical motor skill for childrens cognitive development and academic success. This article presents a new methodology based on electromyographic signals to recognize multi-user free-style multi-stroke handwriting characters. The approach proposes using powerful Deep Learning (DL) architectures for feature extraction and sequence recognition, such as convolutional and recurrent neural networks. This framework was thoroughly evaluated, obtaining an accuracy of 94.85%. The development of handwriting devices can be potentially applied in the creation of artificial intelligence applications to enhance communication and assist people with disabilities.

Autonomous Vehicles (AV) have been extensively studied in both scientific and social contexts. Over the past two decades, there has been a significant rise in their real-world applications, including neural networks, Blockchain, Internet of Things, autonomous navigation, computer vision, automation processes, and various other areas. Hence, it is imperative to investigate the interplay between software, hardware, and individuals. To guarantee secure and unaffected interactions within autonomous vehicle devices and networks, decentralized Blockchain technology is proposed. This study presents the introduction of a framework we named “DEMU-NAV” for an ecosystem that includes Artificial Intelligence (AI), humans, and robots. The framework makes use of a decentralized Blockchain, Smart-Contract (SC), and Internet of things (IoT) network. Our framework was implemented using Ethereum and Python, enabling us to oversee Blockchain, Smart-Contracts, and the IoT for the facilitation of autonomous vehicle navigation.

Research on lithium-ion batteries has been driven by the growing demand for electric vehicles to mitigate greenhouse gas emissions. Despite advances, batteries still face significant challenges in efficiency, lifetime, safety, and material optimization. In this context, the objective of this research is to develop a predictive model based on Deep deep-Learning learning techniques. Based on Deep Learning techniques that combine Transformer and Physicsphysics-Informed informed approaches for the optimization and design of electrochemical parameters that improve the performance of lithium batteries. Also, we present a training database consisting of three key components: numerical simulation using the Doyle–Fuller–Newman (DFN) mathematical model, experimentation with a lithium half-cell configured with a zinc oxide anode, and a set of commercial battery discharge curves using electronic monitoring. The results show that the developed Transformer–Physics physics-Informed informed model can effectively integrate deep deep-learning DNF to make predictions of the electrochemical behavior of lithium-ion batteries. The model can estimate the battery battery-charge capacity with an average error of 2.5% concerning the experimental data. In addition, it was observed that the Transformer could explore new electrochemical parameters that allow the evaluation of the behavior of batteries without requiring invasive analysis of their internal structure. This suggests that the Transformer model can assess and optimize lithium-ion battery performance in various applications, which could significantly impact the battery industry and its use in Electric Vehicles vehicles (EVs).

Vision Transformer (ViT) models are well known for effectively capturing global contextual information through self-attention. In contrast, ConvNeXt’s hierarchical convolutional inductive bias enables the extraction of robust multi-scale features at lower computational and memory cost, making it suitable for deployment in systems with limited annotation and constrained resources. Accordingly, a multi-scale UNet architecture based on a ConvNeXt backbone is proposed for brain tumor segmentation; it is equipped with a spatial latent module and Reverse Attention (RA)-guided skip connections. This framework jointly models long-range context and delineates reliable boundaries. Magnetic resonance images drawn from the BraTS 2021, 2023, and 2024 datasets serve as case studies for evaluating brain tumor segmentation performance. The incorporated multi-scale features notably improve the segmentation of small enhancing regions and peripheral tumor boundaries, which are frequently missed by single-scale baselines. On BraTS 2021, the model achieves a Dice similarity coefficient (DSC) of 0.8956 and a mean intersection over union (IoU) of 0.8122, with a sensitivity of 0.8761, a specificity of 0.9964, and an accuracy of 0.9878. On BraTS 2023, it attains a DSC of 0.9235 and an IoU of 0.8592, with a sensitivity of 0.9037, a specificity of 0.9977, and an accuracy of 0.9904. On BraTS 2024, it yields a DSC of 0.9225 and an IoU of 0.8575, with a sensitivity of 0.8989, a specificity of 0.9979, and an accuracy of 0.9903. Overall, the segmentation results provide spatially explicit contours that support lesion-area estimation, precise boundary delineation, and slice-wise longitudinal assessment.

Cephalometric analysis is a tool to study the craniofacial relationships, commonly used by dentists and orthodontists for skull growth analysis, diagnosis, planning, and treatment. Automatic cephalometric analysis systems rely on the precise labeling of lateral skull radiographs. This task demands from the health expert, an excellent visual acuity, and a significant amount of time in the medical image's manual labeling. This paper proposes a computational tool to support the process of semi-automatic labeling of Lateral Cephalometric Radiographs (LCR). The tool receives as input a set of images corresponding to LCR and performs automatic tasks such as filtering and digital signal processing to assist the health expert on the labeling task, using computational visual human perception models. The tool output is a set of N cephalometric landmarks (x, y) for each LCR. This tool has a set of image preprocessing techniques that clarify the manual labeling getting the accuracy required by the experts. It supports the experts in the cephalometric analysis. The second application is the creation of a new database for the development of automatic cephalometric landmark identification systems.