CRIS

Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1

Browse

Search Results

Now showing 1 - 10 of 167

Some of the metrics are blocked by your
consent settings
Towards a Distributed-Based Learning Robot from Scratch via Neuro-Evolutionary Computation
(Springer Nature Switzerland, 2025)
;
In the context of Industry 4.0, multi-robot systems (MRS) have become essential for enhancing the adaptability and efficiency of flexible manufacturing systems, enabling rapid responses to market demands through personalized customization. Effective collaboration among multiple robots requires advanced communication, shared goal alignment, and the ability to gather and process environmental data to execute coordinated actions with precision. Despite their advantages, improving efficiency of robot learning still remains a crucial challenge, particularly in flexible manufacturing multi-robot systems, where generalization across diverse scenarios is essential for effective deployment. In this work, we propose the use of neuro-evolutionary computation to solve the particular learning-from-scratch problem in a multi-robot system. This approach consists of an architecture of a decentralized MRS in which a local controller per robot is based on Artificial Hydrocarbon Networks machine learning model. Also, it includes a learning strategy via Wound Treatment Optimization algorithm. We implement the architecture in a simulated environment to solve the mountain car domain. Experimental results and a comparison with reinforcement learning validate the ability of this approach to learn a task from scratch without prior explicit data. We anticipate the applicability of this approach in smart factories or autonomous vehicles. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Machine Learning Methods in Biomedical Field : Computer-Aided Diagnostics, Healthcare and Biology Applications
(Springer Nature Switzerland, 2026)
;
;
;
Gomez-Coronel, Sandra L.
;
Renza Torres, Diego
This book provides an in-depth exploration of machine learning techniques and their biomedical applications, particularly in developing intelligent computer-aided diagnostic systems, creating groundbreaking healthcare technologies, uncovering novel biological applications, and fostering sustainable health solutions. Integrating artificial intelligence, mathematical modeling, and emergent systems, this book highlights the profound impact of these advanced tools in not only enhancing problem-solving within the biomedical field but also in catalyzing the development of novel solutions. This book is a valuable resource for readers interested in understanding the revolutionary impact of novel machine learning methodologies on the biomedical landscape. Furthermore, it offers a blend of theory and practical applications for those interested in biomedical education and training, biology, medicine, and sustainable health development. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Orthosis Control Based on Electromyographic Signals and Machine Learning
(Springer Nature Switzerland, 2025)
Escobedo-Gordillo, Andrés
;
Díaz, Fernando
;
Villa, Jesús
;
Sepúlveda, Miguel
;
García-Casas, Sebastián
The human hand is indispensable for daily activities, and those who suffer from dysfunction due to strokes or accidents often require therapy to improve their condition. This study has developed a hand orthosis that uses surface Electromyographic (sEMG) signals and machine learning to address therapeutic needs and improve the quality of life for individuals with reduced motor skills in their hands and/or wrists. While current orthoses meet therapy requirements, they do not incorporate machine learning (ML) or sEMG sensors to optimize performance and accessibility. This chapter describes a remote-controlled, electro-mechanical orthosis that can replicate six basic movements of the human hand using three sEMG channels and ML. Our dataset of 14,400 samples, each labeled with a hand gesture, was generated by eight participants. The orthosis is comfortable and customizable for different users, as shown in prototype testing. The convolutional neural network (CNN) used achieves an accuracy of 90.38% with an inference time of 1.515 ms. Therefore, this orthosis system has significant potential for further development and practical application in patients who require such intervention. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Modular IoT Hydroponics System
(MDPI AG, 2025)
Aranda Barrera, Manlio Fabio
;
Hydroponics offers a promising alternative to soil-based agriculture, enabling higher yields, resource efficiency, and improved crop quality. This study compares traditional hydroponic setups with systems enhanced through the Internet of Things (IoT) framework using the Nutrient Film Technique and a proportional–integral controller, focusing on growth performance and environmental control. Systems incorporating Internet of Things technology achieved a growth rate of 0.94 cm/day versus 0.16 cm/day for conventional setups, due to precise water temperature control, optimized lighting, data acquisition, targeted nutrients, and reduced pest incidence. The integration of Industry 4.0 principles further enhances sustainable production and resource management. Statistical validation under diverse conditions is recommended. Future work will add environmental sensors, refine mechanical design, and explore machine learning for adaptive control, highlighting the potential of Internet of Things–based hydroponics to transform agriculture through intelligent, efficient, and eco-friendly cultivation. ©The authors ©MDPI.
Some of the metrics are blocked by your
consent settings
Design and Prototyping of a Bio-inspired Robotic Tail
(Springer Nature Switzerland, 2025)
;
Ramírez, Alexia
Bio-inspired robotics, which involves observing and replicating the behavior of natural systems, has driven significant innovation in the technical development of robotic components. A primary objective within this field is to emulate the sophisticated internal functions of animals to solve complex engineering challenges, such as control and stability. While the integration of bio-mimetic tails in robotic systems is not new, with applications ranging from running to walking robots, existing designs are often limited in their functionality. Currently, most robotic tails primarily offer stability within static or limited dynamic contexts. The objective of this work is to design a preliminary robotic tail inspired by the chameleon’s tail, using hard and soft materials. Design and prototyping are discussed in the paper. We anticipate that this robotic tail can be used in the context of dynamic stability of quadruped robots. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Predicting Substance Addiction in University Students: A DSM-5-Guided Machine Learning Model
(Springer Nature Switzerland, 2025-10-24)
González Bustamante, Pablo
;
Substance use among university students is a growing health concern that is often overlooked until it escalates into a full-grown disorder. This study presents a multiclass machine learning model for predicting substance use risk levels based on DSM-5 diagnostic criteria and psychosocial factors such as trauma, academic stress and social networks. Data were collected through a survey answered by university students, the resulting dataset was used to train and compare multiple models. After performing feature selection, class balancing and hyperparameter tuning, the best performing and most accurate model, was a logistic-regression model that achieved a macro F1-score of 0.946. More notably however, the model showed improved sensitivity for mild-risk cases, which tend to go underdetected in binary classification schemes. These results support the integration of clinically based machine learning models, into educational institutions health protocols. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Pre-trained Models for Grammatical Error Correction in Healthcare-Specific Text
(Springer Nature Switzerland, 2025)
González Mora, José Guillermo
;
Grammatical Error Correction (GEC) is a common Natural Language Processing task and has been studied extensively in the field. There is an added complexity when trying to correct domain-specific text that is uncommon in general-purpose corpora. In this paper, we present a comparative study of three different approaches using pre-trained language models for Grammatical Error Correction in healthcare-specific text. We evaluated the performance of all proposals using the GLEU score metric, which allows a quantitative comparison of all methods. We utilized two different problem settings: first, a sequence-to-sequence pre-trained T5 model, followed by a fine-tuning process over a small set of examples. The second model is a pre-trained large language model, for which we test both zero-shot and few-shot in-context learning. The study shows how the fine-tuned T5 model is capable of exceeding the performance shown by the LLM tested. With this result, we show how smaller encoder-decoder models can solve domain-specific tasks with fewer parameters than a purely generative pre-trained LLM. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Metaheuristic Strategy in Automatic Robotics Navigation for Patient Care in Hospitals
(Springer Nature Switzerland, 2025)
Monroy-Rueda, Irvine J.
;
;
;
This chapter presents a novel approach for developing a global automatic navigation strategy for a mobile robot for patient care into health centers and hospitals. The proposal uses a metaheuristic strategy through the Grey Wolf Optimizer algorithm to find the shortest route between the robot’s starting and patient destination points, while also integrating knowledge of the environment acquired through vision. The global navigation tracking is achieved through the use of Fuzzy Logic Rules to control the robot’s wheel velocity according to its current position and orientation. The proposed strategy was implemented in a virtual robotics environment demonstrating that the approach successfully generated optimal paths for various environments with a minimal number of control points and in a relatively short amount of time. In addition, a simulated hospital room with common furniture and tasks was used to evaluate the performance of the global navigation strategy, demonstrating that the robot could successfully generate a global route and navigate within this environment. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Automatic Robotics Medication Delivery System: The ANDIS Case Study
(Springer Nature Switzerland, 2025)
Carbajal, Pablo
;
Cobb, Ethan
;
Hernández, César
;
Mejía, Alfredo
;
Menchaca, Lucía
Hospitals face challenges such as nurse burnout and unproductive time utilization. Interviews with nurses and physicians revealed that 75% of their workday is dedicated to patient care and the remaining 25% could be considered unproductive due to other tasks such as manual record-keeping, canceled surgeries and postponed procedures. Streamlining tasks can free up nurses’ time for better patient care. One of these tasks is medication delivery, which can be automated using autonomous delivery robots. In this regard, we propose the design of a small autonomous robot that delivers drugs inside hospitals to reduce the medical staff’s workload. The proposed robotics system uses ultrasonic sensors and fuzzy logic control for the avoidance of obstacle tasks. In addition, an AI camera and color indicators are used to identify the room and follow the designed trajectory to deliver the medication. Results showed that the robot navigates without colliding, and the final distance between the robot and the indicators was considered appropriate for medication delivery tasks. Furthermore, its maintenance is straightforward due to its uncomplicated mechanical design. Finally, the non-invasive nature of the colored indicators minimizes the visual impact on hospital environments. ©The authors © Spring.
Some of the metrics are blocked by your
consent settings
Preface : Machine Learning Methods in Biomedical Field Computer-Aided Diagnostics, Healthcare and Biology Applications
(Springer Science and Business Media Deutschland GmbH, 2026)
;
;
;
Gomez-Coronel, Sandra L.
;
Renza Torres, Diego
This book presents a multidisciplinary collection of machine learning approaches applied to the biomedical field, with a focus on computer-aided diagnostic systems, healthcare support tools, biological applications, and sustainable development in health. Computer-aided diagnostic systems leverage machine learning methods to support medical diagnosis, while healthcare support tools, biological applications, and sustainability-oriented studies aim to improve patients’ quality of life, propose innovative solutions to biological challenges, and incorporate sustainability into healthcare processes. The contributions in this book offer readers a holistic view of new methods used to address current biomedical challenges in medicine, biology, and health sciences. By applying artificial intelligence algorithms, mathematical theories, and emergent systems, these works demonstrate how such approaches can improve specific problems or propose innovative solutions. This book is valuable for readers interested in recent advances in machine learning for diagnostic systems, healthcare applications, biological research, and sustainability-related issues. ©The authors ©Springer.

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results