Browsing by Subject "Prediction"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Publication
    Open Access
    A review of the limitations of financial failure prediction research
    (Universidad de Murcia, Servicio de Publicaciones, 2023) Laitinen, Erkki K.; Camacho-Miñano, María-del-Mar; Muñoz-Izquierdo, Nora
    The objective of this paper is to critically evaluate the main weaknesses associated with the limitations of financial failure prediction research studies. For more than 80 years, researchers have unsuccessfully studied ways to create a general theory of financial failure, which is useful for prediction. In this paper, we review the main boundaries of failure prediction research through a critical evaluation of previous papers and our own approach from the research experience. Our findings corroborate that these studies suffer from a lack of theoretical and dynamic research, an unclear definition of failure, deficiencies with the quality of financial statement data and a shortfall in the diagnostic analyses of failure. The most relevant implications for future research in this area are also outlined. This is the first study to analyse in deep the caveats of financial failure prediction studies, a crucial topic nowadays due to the hints of an economic crisis caused by the Covid-19 pandemic.
  • Thumbnail Image
    Publication
    Open Access
    Estimation of nitrogen content in cucumber plant (Cucumis sativus L.) leaves using hyperspectral imaging data with neural network and partial least squares regressions
    (Elsevier, 2021-10-15) Sabzi, Sajad; Pourdarbani, Razieh; Rohban, Mohammad H.; García Mateos, Ginés; Arribas, J. I.; Informática y Sistemas; Facultades de la UMU::Facultad de Informática
    In recent years, farmers have often mistakenly resorted to overuse of chemical fertilizers to increase crop yield. However, excessive consumption of fertilizers might lead to severe food poisoning. If nutritional deficiencies are detected early, it can help farmers to design better fertigation practices before the problem becomes unsolvable. The aim of this study is to predict the amount of nitrogen (N) content in cucumber (Cucumis sativus L., var. Super Arshiya-F1) plant leaves using hyperspectral imaging (HSI) techniques and three different regression methods: a hybrid artificial neural networks-particle swarm optimization (ANN-PSO); partial least squares regression (PLSR); and unidimensional deep learning convolutional neural networks (CNN). Cucumber plant seeds were planted in 20 different pots. After growing the plants, pots were categorized and three levels of nitrogen overdose were applied to each category: 30%, 60% and 90% excesses, called N30%, N60%, N90%, respectively. HSI images of plant leaves were captured before and after the application of nitrogen excess. A prediction regression model was developed for each individual category. Results showed that mean regression coefficients (R) for ANN-PSO were inside 0.937–0.965, PLSR 0.975–0.997, and CNN 0.965–0.985 ranges, test set. We conclude that regression models have a remarkable ability to accurately predict the amount of nitrogen content in cucumber plants from hyperspectral leaf images in a non-destructive way, being PLSR slightly ahead of CNN and ANN-PSO methods.
  • Thumbnail Image
    Publication
    Open Access
    Factores del rendimiento académico en los estudios de Arquitectura
    (Universidad de Murcia, 1989) Toca, María Teresa; Tourón Figueroa, Javier
    Hemos realizado un estudio de regresión múltiple con el objeto de llegar a establecer cuáles son algunos de los factores que mayor repercusión tienen en el rendimiento académico de los alumnos que acceden a la carrera de Arquitectura en la Escuela Técnica Superior de la Universidad de Navarra. Las variables que se han manejado en este estudio han recogido información sobre los siguientes aspectos: aptitudes diferenciales de la inteligencia, ASAT (Architectural Scholastic Aptitude Test), Pruebas de Admisión de la ETS de Arquitectura, rendimientos académicos previos y rendimientos académicos en la Universidad. Han sido calculadas dos ecuaciones de regresión múltiple para cada asignatura de primer curso. Los R múltiples han arrojado valores entre 0,39 y 0,83, lo que supone porcentajes de varianza explicadas entre el 15% y eI 68%. Nuestros resultados han confirmado los de numerosas investigaciones, ya que han puesto de manifiesto, una vez más, que el rendimiento previo es el mejor predictor del rendimiento futuro.
  • Thumbnail Image
    Publication
    Open Access
    Machine learning application in soccer: a systematic review
    (Termedia Publishing, 2022-03-16) Rico-González, Markel; Méndez, Amaia; Clemente, Filipe Manuel; Baca, Arnold; Pino Ortega, José; Actividad Física y Deporte
    Due to the chaotic nature of soccer, the predictive statistical models have become in a current challenge to decision-making based on scientific evidence. The aim of the present study was to systematically identify original studies that applied machine learning (ML) to soccer data, highlighting current possibilities in ML and future applications. A systematic review of PubMed, SPORTDiscus, and FECYT (Web of Sciences, CCC, DIIDW, KJD, MEDLINE, RSCI, and SCIELO) was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. From the 145 studies initially identified, 32 were fully reviewed, and their outcome measures were extracted and analyzed. In summary, all articles were clustered into three groups: injury (n = 7); performance (n = 21), which was classified in match/league outcomes forecasting, physical/physiological forecasting, and technical/tactical forecasting; and the last group was about talent forecasting (n = 5). The development of technology, and subsequently the large amount of data available, has become ML in an important strategy to help team staff members in decision-making predicting dose-response relationship reducing the chaotic nature of this team sport. However, since ML models depend upon the amount of dataset, further studies should analyze the amount of data input needed make to a relevant predictive attempt which makes accurate predicting available.
  • Thumbnail Image
    Publication
    Open Access
    Research progress on the correlation between platelet aggregation and tumor progression
    (Universidad de Murcia. Departamento de Biología Celular e Histología, 2024) Chen, Yuyu; Yuan, Jialong; Tang, Faqing; Liu, Qinglin; Huang, Hongjun; Liu, Huan; Liu, Hao
    Platelets are generally considered as the main functional unit of the coagulation system. However, more and more studies have confirmed that platelets also have an important relationship with tumor progression. Tumor cells can utilize platelets to promote their own infiltration and hematogenous metastasis, and platelets are activated and aggregated in this process. Therefore, platelet aggregation may be a concomitant marker of tumor progression. This is of great significance for predicting tumor metastasis before timely treatments.
  • Thumbnail Image
    Publication
    Open Access
    The impact of rule updates on the performance of racewalkers and the classification of countries: An analysis at the Olympic Games
    (Universidad de Murcia, Servicio de Publicaciones, 2024) Megahed, Mohamed; Tarek, Zahraa
    Numerous controversies arose over the judgment of the racewalking events, and the rules were amended more than once. Before 1995, the rule required constant touch with the ground, and the need for a straight knee was only applied in the upright vertical posture. While, after 1995, the rule that applies today was published, which included two obvious changes. One related to maintaining a constantly straight knee through the first half of the stride, and the other to maintaining contact as seen by the human eye. This study aimed to investigate the impact of the last three modifications in racewalking rules on elite athletes' performance, athletes' eligibility, and nations' classification. Also, we investigated the regression between performance times of 20, and 50 km events and explanatory variables (BMI, and age). We collected data of 310 racewalkers from Olympic Games records (men) in 20km and 50km between 1956 and 2016. This period was divided into three stages according to the racewalking rules updates: Stage A (from 1996 to 2016), Stage B (from 1976 to 1992), and Stage C (from 1956 to 1972). There was a significant difference between all stages favoring stage A for Athlete’s Performance. Stage A has the highest speeds (4.06±.23m/sec) for 20km with large ES (η2=.54, p=.000), and (3.71±.06m/sec) for 50km with large ES (η2=.769, p=.000) compared to others. The participants had the efficiency and the ability to finish the race with the least percentage of withdrawals under the current rule compared to other rules. Some countries emerged on the scene, i.e. China, Poland and Ecuador, and others disappeared under the current rule; while the regression model's results revealed a substantial link between time and explanatory parameters where (BConstant=58.219, P.000) for 20km and (BConstant=164.744, P.000) for 50km. Results proved that the elite walkers, the youngest and lowest in BMI, are the fastest and most efficient walkers under the current rule