Article
Medical Informatics
Maryam Ahmadi, Raoof Nopour
Summary: This study aimed to develop a CDSS based on ANN to improve the quality of life among elderly individuals by considering physical, psychiatric, and social factors. Results indicated that the CF-BP model had the best performance for predicting the quality of life among the elderly.
BMC MEDICAL INFORMATICS AND DECISION MAKING
(2022)
Article
Computer Science, Artificial Intelligence
Prashant Kumar Singh, Prabir Sarkar
Summary: This study aims to develop an AI tool to assist designers in choosing environmentally friendly design parameters. The tool is based on an ANN model and predicts the carbon footprint and life cycle cost of a product. The tool has a high accuracy of over 90% and is significantly more time-efficient than other assessment tools.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Health Care Sciences & Services
I-Li Lin, Jean Yu-Chen Tseng, Hui-Ting Tung, Ya-Han Hu, Zi-Hung You
Summary: In this study, machine learning techniques were used to develop models for predicting the risk of future multiple suicide attempts among psychiatric patients. Results showed that the Adaboost+DT model performed the best in predicting the behavior of multiple suicide attempts. These findings can aid clinical staffs in early identifying high-risk patients and improving the effectiveness of suicide prevention.
Article
Mathematics
Mohd Shareduwan Mohd Kasihmuddin, Siti Zulaikha Mohd Jamaludin, Mohd Asyraf Mansor, Habibah A. Wahab, Siti Maisharah Sheikh Ghadzi
Summary: This paper proposes a novel logic mining approach that combines association analysis and supervised learning to identify and obtain the optimal induced logic rule, thus improving the performance of logic mining.
Article
Biochemistry & Molecular Biology
Antonio Agliata, Deborah Giordano, Francesco Bardozzo, Salvatore Bottiglieri, Angelo Facchiano, Roberto Tagliaferri
Summary: Diabetes is a chronic metabolic disease with high blood sugar levels, and type 2 diabetes is the most common type. Early diagnosis and treatment can prevent or delay complications. Previous studies have used machine learning techniques to predict diabetes, and artificial neural networks have shown promising results as a valuable tool for diabetes management and prevention. The study used machine learning methods to uncover associations between health status and the development of type 2 diabetes, aiming to accurately predict its onset or determine the individual's risk level.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Alexander J. Dyer, Lewis D. Griffin
Summary: Inferring the connectivity of biological neural networks from neural activation data is challenging, but studying the analogous problem in artificial neural networks can provide insights into the biological case. This study focuses on assigning artificial neurons to locations in the LeNet image classifier. A supervised learning approach based on features derived from the activation correlation matrix is evaluated. The experiments suggest that an image dataset needs to fully activate the network and have minimal confounding correlations for accurate localization, and perfect assignment can be achieved by combining features from multiple image datasets.
Article
Chemistry, Multidisciplinary
Lukasz Apiecionek, Rafal Mos, Dawid Ewald
Summary: The research aims to design an artificial neural network that requires less computational power for assessing quality of life. The development of the mentioned ANN was possible due to the application of fuzzy logic, especially ordered fuzzy numbers (OFN). OFN has been applied to various issues, such as detecting network attacks, anticipating server load, managing data transmission paths, and improving quality of life.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Multidisciplinary
Adeeb Noor, Liaqat Ali, Hafiz Tayyab Rauf, Usman Tariq, Saima Aslam
Summary: Heart failure is a life-threatening disease, and it is important to predict associated risks early on. Existing medical decision support systems have focused on feature transformation methods and machine learning models, but there are issues with performance and accuracy. This study proposes a more robust approach that integrates stacked autoencoders with a neural network model to improve classification accuracy.
Article
Chemistry, Analytical
Puneet Mishra, Douglas N. Rutledge, Jean-Michel Roger, Khan Wali, Haris Ahmad Khan
Summary: Pre-processing of NIR spectral data may decrease predictive performance, especially when scatter correction techniques are used. In this study, Deep Learning models outperformed Partial Least Squares regression in efficiently modeling raw absorbance data.
Article
Medical Laboratory Technology
Christopher-John L. Farrell
Summary: This study found that human supervision can improve the accuracy of AI models in identifying WBIT errors, but autonomous AI models outperform human-supervised models in recognizing such errors, achieving higher accuracy, sensitivity, and specificity.
CLINICAL CHEMISTRY AND LABORATORY MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Siqi Wang, Tee Hiang Cheng, Meng Hiot Lim
Summary: This paper reviews the importance of Artificial Neural Network (ANN) in machine learning and artificial intelligence, explores the potential of Spiking Neural Network (SNN) in compact embedded AI, and discusses the current research status of SNN training techniques and weight updating algorithms.
Article
Mathematics, Interdisciplinary Applications
Wei-Chang Yeh, Yunzhi Jiang, Shi-Yi Tan, Chih-Yen Yeh
Summary: The paper introduces a novel convolutional SVM (CSVM) that combines the advantages of CNN and SVM to improve accuracy and effectiveness in mining smaller datasets. Experimental results show that the proposed CSVM with a modified simplified swarm optimization (SSO) can effectively increase classification accuracy.
Article
Computer Science, Software Engineering
Saba Kalantary, Reza Pourbabaki, Ali Jahani, Mohsen Sadeghi Yarandi, Sajjad Samiei, Reza Jahani
Summary: The study used artificial neural networks to classify spirometry data of 130 subjects, demonstrating the multi-layer perceptron model's ability to accurately classify respiratory abnormalities in different individuals.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2021)
Article
Health Care Sciences & Services
Federico Baldisseri, Arturo Maiani, Edoardo Montecchiani, Francesco Delli Priscoli, Alessandro Giuseppi, Danilo Menegatti, Vincenzo Fogliati
Summary: This study focuses on the use of artificial intelligence in supporting the neurorehabilitation of children with brain injuries or neurological difficulties through the implementation of a mobile app. The app includes games for pediatric patients to play, allowing them to recover cognitive and motor abilities while engaging in enjoyable activities. The study proposes a Neural Network Classification approach to adapt the game difficulty based on the child's current cognitive capabilities.
Article
Computer Science, Interdisciplinary Applications
Ki Hyun Kim, Gil Ho Yoon
Summary: In this study, we investigate the feasibility of using an artificial neural network (ANN) model for solving the inverse problem in determining the voltage conditions for achieving specific deformations in a dielectric elastomer actuator (DEA). We focus on two approaches based on supervised learning. The first approach utilizes ANN to replace the finite element analysis (FEA) in computing the forward problem of DEA, while the second approach directly solves the inverse problem using ANN. The first approach is more accurate for abstract target deformations, while the second approach performs better for more realistic target deformations. Overall, this study scores 8 out of 10.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2023)
Review
Biochemistry & Molecular Biology
Miranda Hernandez-Falco, Paula Saez-Espinosa, Andrea Lopez-Botella, Jon Aizpurua, Maria Jose Gomez-Torres
Summary: This study aimed to summarize the current knowledge about IZUMO1 and TMEM95 during mammalian fertilization. The results showed that IZUMO1 is mostly studied in rodents whereas TMEM95 is studied primarily in bovines. IZUMO1 may be involved in organizing or stabilizing a multiprotein complex essential for membrane fusion, while TMEM95 may act as a fusogen due to its possible interaction with IZUMO1. However, the expression of these two proteins alone is not sufficient for sperm-oocyte fusion, suggesting the involvement of other molecules.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Reproductive Biology
Paula Saez-Espinosa, Cristina Franco-Esclapez, Laura Robles-Gomez, Willian T. A. F. Silva, Alejandro Romero, Simone Immler, Maria Jose Gomez-Torres
Summary: The study revealed significant morphological and ultrastructural changes in zebrafish spermatozoa after motility activation, including distortion of the head and damage to the midpieces.
Article
Green & Sustainable Science & Technology
Guillermo Almonacid-Olleros, Gabino Almonacid, David Gil, Javier Medina-Quero
Summary: This paper discusses the capabilities of deep learning models to predict energy generation in different regions and deployments, and analyzes the impact of transfer learning on energy prediction.
Article
Obstetrics & Gynecology
Maria Jose Gomez-Torres, Natalia Huerta-Retamal, Paula Saez-Espinosa, Laura Robles-Gomez, Manuel Aviles, Jon Aizpurua
Summary: In this study, the presence and spatial location of HSPA2 on human spermatozoa were evaluated based on its hyaluronic acid binding capacity. The results showed that HSPA2 may play an important role in male fertility, and the hyaluronic acid selection technique and HSPA2 biomarker could potentially complement the classic seminal analysis.
REPRODUCTIVE SCIENCES
(2023)
Article
Biochemistry & Molecular Biology
Maria Jose Gomez-Torres, Paula Saez-Espinosa, Paula Manzano-Santiago, Laura Robles-Gomez, Natalia Huerta-Retamal, Jon Aizpurua
Summary: This study characterized the distribution of SPAM1 in different physiological conditions of human sperm and found that the presence of SPAM1 throughout the sperm head is necessary for proper contact with the cumulus-oocyte matrix.
Article
Biochemistry & Molecular Biology
Irene Peinado, Isabel Moya, Laura Garcia-Valverde, Raquel Frances, Rosana Ribes, Patrocinio Polo, Maria Jose Gomez-Torres, Ana Monzo
Summary: This study explores the impact of in vitro maturation (IVM) medium and vitrification on the survival and development of germinal vesicle (GV) oocytes obtained from stimulated cycles. The results show that a higher percentage of oocytes reach the MII stage if they are vitrified before undergoing IVM. However, the significance of these differences depends on the medium used and sample size. Similar survival rates and development to blastocysts were observed in all conditions studied.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Review
Biology
Julia Andreu-Noguera, Andrea Lopez-Botella, Paula Saez-Espinosa, Maria Jose Gomez-Torres
Summary: This review provides a detailed overview of current knowledge in the field of spermatozoa epigenetics and its implications. A full search was conducted through three databases, resulting in a collection of 485 scientific publications. The bibliographic overview showed that sperm epigenetics is an active and growing research area, and the normal performance of sperm heavily relies on its epigenetics, which can explain reproductive pathologies or abnormal inheritance. This study area is burgeoning and has the potential to provide society with clinical innovations in a short-term period.
Article
Biochemistry & Molecular Biology
Maria Jose Gomez-Torres, Javier Luna-Romero, Pedro Jose Fernandez-Colom, Jon Aizpurua, Manuel Aviles, Alejandro Romero
Summary: Nuclear vacuoles are specific structures present on the head of the human sperm. This study aimed to define the incidence, position, morphology, and molecular content of the human sperm vacuoles. Results showed that approximately 50% of analyzed human sperm cells contained vacuoles, mainly located in the anterior head region. Furthermore, it was discovered that these vacuoles were invaginations of the nuclear envelope containing cytoskeletal proteins and a cytoplasmic enzyme.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Environmental Sciences
Andrea Lopez-Botella, Raquel Sanchez, Jose-Luis Todoli-Torro, Maria Jose Gomez-Torres, Irene Velasco, Maribel Acien
Summary: Toxic metals in the environment are linked to female infertility and gynecological illnesses. A reliable analytical method called ICP-MS/MS was optimized to determine the elemental composition of peritoneal fluid samples. The method was validated and applied to analyze the concentrations of various elements in 20 samples.
Review
Biology
Andrea Lopez-Botella, Raquel Sanchez, Raiza Paul, Jon Aizpurua, Maria Jose Gomez-Torres, Jose-Luis Todoli-Torro
Summary: Infertility is a growing concern affecting 15% of couples worldwide. Chemical contaminants, specifically heavy metals, have been identified as important factors leading to infertility problems. This review highlights the detection and quantification of heavy metals in human seminal plasma using techniques like atomic absorption spectroscopy and inductively coupled plasma. Accurate quantification of endocrine-disrupting compounds in seminal plasma can aid in the development of personalized therapy for male infertility.
Review
Computer Science, Interdisciplinary Applications
Sandra Amador, Felix Beuschlein, Vedant Chauhan, Judith Favier, David Gil, Phillip Greenwood, R. R. de Krijger, Matthias Kroiss, Samanta Ortuno-Miquel, Attila Patocs, Anthony Stell, Axel Walch
Summary: This article reviews the application of deep learning techniques in the detection or segmentation of renal tumors. The review provides detailed information on research objectives, data sets used, and the number of patients involved. The importance of open data sharing in this field is emphasized.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Biochemistry & Molecular Biology
Maria Jose Gomez-Torres, Miranda Hernandez-Falco, Andrea Lopez-Botella, Natalia Huerta-Retamal, Paula Saez-Espinosa
Summary: This study describes the distribution of IZUMO1 in human sperm under different physiological conditions. The results show that IZUMO1 is mainly located in the acrosomal region, and a new distribution pattern suggests the migration of IZUMO1. The study also reveals various combinations between the IZUMO1 staining patterns and the acrosomal stages.
Proceedings Paper
Computer Science, Artificial Intelligence
Maria del Mar Guillen, Sandra Amador, Jesus Peral, David Gil, Aya Elouali
Summary: This paper presents a modular and scalable architecture for the prediction and treatment of autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD). The architecture allows therapists to collect personalized data from individuals using mobile devices, enabling personalized monitoring. Initial results are very encouraging, despite the small volume of data, as it allows for the development of personalized dashboards for individualized treatment.
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON UBIQUITOUS COMPUTING & AMBIENT INTELLIGENCE (UCAMI 2022)
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Angel Lloret, Juan Carlos Valera, David Gil, Jesus Peral, Antonio Ferrandez, Sandra Amador
Summary: This paper presents a proposal for deploying sensors in supervised housing, discussing the challenges and opportunities involved. The unique characteristics of individuals living in these homes, often with disabilities, make this project a significant social challenge for their inclusion in society.
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON UBIQUITOUS COMPUTING & AMBIENT INTELLIGENCE (UCAMI 2022)
(2023)
Meeting Abstract
Agriculture, Dairy & Animal Science
M. Balastegui-Alarcon, I. Lamas-Toranzo, C. Moros-Nicolas, L. Gonzalez Brusi, P. Soria, P. Cots-Rodriguez, B. Algarra, J. Ballesta, P. Saez-Espinosa, M. J. Gomez-Torres, J. S. Vicente, F. Marco-Jimenez, M. J. Izquierdo-Rico, P. Bermejo, M. Aviles
REPRODUCTION IN DOMESTIC ANIMALS
(2022)