Article
Engineering, Civil
Julien Monteil, Anton Dekusar, Claudio Gambella, Yassine Lassoued, Martin Mevissen
Summary: This work investigates the use of deep learning models for long-term large-scale traffic prediction tasks, focusing on scalability. By analyzing 14 weeks of speed observations from over 1000 segments in downtown Los Angeles, different machine learning and deep learning predictors were studied, along with their scalability to larger areas. The study shows that modeling temporal and spatial features into deep learning predictors can be beneficial for long-term predictions, while simpler predictors achieve satisfactory performance for link-based and short-term forecasting, with a trade-off in prediction accuracy, horizon, training time, and model sizing discussed.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Business, Finance
Amine Mtiraoui, Heni Boubaker, Lotfi BelKacem
Summary: This study proposes an innovative hybrid model, combining autoregressive fractionally integrated moving average (ARFIMA), empirical wavelet (EW) transform, and local linear wavelet neural network (LLWNN) approaches, to predict Bitcoin returns and volatilities. The model integrates the advantages of the long memory model, EW decomposition technique, artificial neural network structure, and back propagation and particle swarm optimization learning algorithms. Experimental results show that the optimized hybrid approach outperforms classic models in terms of providing accurate out-of-sample forecasts over longer horizons. The model proves to be the most appropriate Bitcoin forecasting technique, with smaller prediction errors compared to other computing techniques.
RESEARCH IN INTERNATIONAL BUSINESS AND FINANCE
(2023)
Article
Multidisciplinary Sciences
Vitor Hugo Serravalle Reis Rodrigues, Paulo Roberto de Melo Barros Junior, Euler Bentes dos Santos Marinho, Jose Luis Lima de Jesus Silva
Summary: Developing accurate models for groundwater control is crucial for managing and planning water resources from aquifer reservoirs. The proposed Wavelet Gated Multiformer combines the strengths of a vanilla Transformer and a Wavelet Crossformer to improve the model's predictive capabilities by computing the relationships between time-series points and finding trending periodic patterns. This model outperforms other transformer-like models in terms of Mean Absolute Error reduction.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Jun-Jie Huang, Pier Luigi Dragotti
Summary: The proposed WINNet method combines the advantages of wavelet-based methods and learning methods for image denoising, containing LINNs, sparse coding denoising, noise estimation networks, etc. By implementing nonlinear redundant transforms, sparse coding, and adaptively adjusting soft thresholds, WINNet method demonstrates strong generalization ability across different noise levels.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Rakshitha Godahewa, Kasun Bandara, Geoffrey Webb, Slawek Smyl, Christoph Bergmeir
Summary: Ensembling techniques are used to improve the performance of Global Forecasting Models (GFM) and univariate models in heterogeneous datasets. A new clustered ensembles methodology is proposed to train multiple GFMs on different clusters of series, achieving higher accuracy than baseline models.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Yin Su, Cuili Yang, Junfei Qiao
Summary: The self-organizing PRWNN (SPRWNN) is a neural network model that automatically adjusts the network structure by using the spiking strength of nodes and the module growth mechanism. Experimental results show that SPRWNN improves the prediction accuracy by about 40% compared to the PRWNN with fixed structure.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Konstantinos Benidis, Syama Sundar Rangapuram, Valentin Flunkert, Yuyang Wang, Danielle Maddix, Caner Turkmen, Jan Gasthaus, Michael Bohlke-Schneider, David Salinas, Lorenzo Stella, Francois-Xavier Aubet, Laurent Callot, Tim Januschowski
Summary: Deep learning based forecasting methods have achieved remarkable success in time series prediction and have become widely used in industrial applications and forecasting competitions. This article provides an introduction to deep forecasting, discussing important building blocks and summarizing recent literature.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen, Bin Yang, Shirui Pan
Summary: This paper proposes a continuous model, MTGODE, to forecast multivariate time series by overcoming the limitations of discrete neural architectures, high complexity, and reliance on graph priors. MTGODE utilizes dynamic graph neural ordinary differential equations to unify spatial and temporal message passing, resulting in superior forecasting performance on benchmark datasets.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Madhurima Panja, Tanujit Chakraborty, Uttam Kumar, Nan Liu
Summary: Infectious diseases continue to be a major cause of illness and death worldwide, with epidemic waves of infection. The lack of specific drugs and vaccines exacerbates the situation, leading to a reliance on accurate and reliable epidemic forecasters. The proposed Ensemble Wavelet Neural Network (EWNet) model effectively characterizes the non-stationary behavior and seasonal dependencies of epidemic time series, improving the accuracy of epidemic forecasting compared to other methods.
Article
Computer Science, Artificial Intelligence
Xuxiang Ta, Zihan Liu, Xiao Hu, Le Yu, Leilei Sun, Bowen Du
Summary: Accurate traffic forecasting is crucial for intelligent transportation systems. Existing research often uses Spatio-Temporal Graph Neural Networks (ST-GNNs) to capture spatiotemporal correlations, but the utilization of node attributes for better graph structure learning is limited. This paper proposes an Adaptive Spatio-Temporal graph neural Network (Ada-STNet) that derives optimal graph structure with the guidance of node attributes and captures complex spatiotemporal correlations for traffic condition forecasting.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Lifan Long, Qian Liu, Hong Peng, Qian Yang, Xiaohui Luo, Jun Wang, Xiaoxiao Song
Summary: A novel time series forecasting approach based on nonlinear spiking neural P systems is proposed in this study. By converting the time series into the frequency domain and automatically constructing and training NSNP systems in the frequency domain, sequence data for future time can be predicted. Experimental results demonstrate the availability and effectiveness of this approach on multiple time series datasets.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Atif Mahmood, Miss Laiha Mat Kiah, Saaidal Razalli Azzuhri, Muhammad Mustafa Kamal, Tillal Eldabi, Adnan N. Qureshi, Zati Hakim Azizul, Muhammad Reza Z'aba
Summary: The shift from hardware to intelligent solutions in technology development has led to new challenges in optimizing resource orchestration. Capacity optimization is crucial in wireless backhaul networks, with dynamic resource allocation methods and three different models improving system performance and reducing resource wastage.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Computer Science, Information Systems
Zhong Zheng, Zijun Zhang, Long Wang, Xiong Luo
Summary: This paper proposes a denoising temporal convolutional recurrent autoencoder (DTCRAE) to enhance the performance of the temporal convolutional network (TCN) in time series classification (TSC). The results of computational studies demonstrate that DTCRAEs outperform other algorithms on three datasets, achieving higher accuracies and providing a better initial structure for TCN classifiers.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Artemios-Anargyros Semenoglou, Evangelos Spiliotis, Vassilios Assimakopoulos
Summary: Data augmentation techniques can improve forecasting accuracy in univariate time series prediction, especially when deep neural networks are used. However, these improvements become less significant as the initial size of the training set increases.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Zimeng Lyu, Alexander Ororbia, Travis Desell
Summary: Time series forecasting is an important task in data science, but offline-trained models often face data drift issues. To address this, this paper proposes an online neural architecture search algorithm (ONE-NAS) that can automatically design and train recurrent neural networks for online forecasting tasks. Experimental results show that ONE-NAS outperforms traditional statistical methods and using multiple populations of RNNs can significantly improve performance.
APPLIED SOFT COMPUTING
(2023)
Article
Health Care Sciences & Services
Nidal Drissi, Sofia Ouhbi, Mohamed Adel Serhani, Goncalo Marques, Isabel de la Torre Diez
Summary: This study presents a synthesis of global attitudes toward connected mental health (CMH) use and the use of technology in mental care. It found that the investigated cohorts generally had positive attitudes towards CMH use and had high levels of technology use and ownership. Preferred criteria for CMH use were identified, and concerns related to technology access, digital divide, and lack of knowledge and reservations towards CMH were addressed.
TELEMEDICINE AND E-HEALTH
(2023)
Article
Computer Science, Artificial Intelligence
Ashok Vajravelu, K. S. Tamil Selvan, Muhammad Mahadi Bin Abdul Jamil, Anitha Jude, Isabel de la Torre Diez
Summary: Wireless Capsule Endoscopy (WCE) enables non-invasive and painless direct visual inspection of the entire digestive system. This research introduces a new approach to extract color information and differentiate bleeding frames from normal frames, as well as locate bleeding areas.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2023)
Article
Chemistry, Analytical
Zaid Bin Faheem, Abid Ishaq, Furqan Rustam, Isabel de la Torre Diez, Daniel Gavilanes, Manuel Masias Vergara, Imran Ashraf
Summary: With the advancement in information technology, digital data stealing and duplication have become easier. Cryptography and image watermarking provide multiple security services. In this paper, a digital image watermarking technique is proposed that employs the least significant bit (LSB) and canny edge detection method. The proposed method provides better security services and is computationally less expensive, and it shows high robustness to image processing and geometrical attacks.
Article
Psychology, Clinical
Susel Gongora Alonso, Isabel Herrera Montano, Juan Luis Martin Ayala, Joel J. P. C. Rodrigues, Manuel Franco-Martin, Isabel de la Torre Diez
Summary: Currently, high hospital readmission rates have become a problem for mental health services. This study aims to predict the readmission risk of patients with schizophrenia in a region of Spain using machine learning algorithms. The Random Forest classifier obtained the best results in predicting the readmission risk, demonstrating the potential of machine learning models in improving patient care quality and developing preventive treatments.
INTERNATIONAL JOURNAL OF MENTAL HEALTH AND ADDICTION
(2023)
Article
Genetics & Heredity
Ali Raza, Furqan Rustam, Hafeez Ur Rehman Siddiqui, Isabel de la Torre Diez, Begona Garcia-Zapirain, Ernesto Lee, Imran Ashraf
Summary: This study focuses on predicting genetic disorders using artificial intelligence-based methods. It proposes a novel feature engineering approach and classifier chain approach, and evaluates the performance using multiple evaluation metrics. Results show that extreme gradient boosting (XGB) outperforms state-of-the-art approaches in terms of both performance and computational complexity.
Article
Plant Sciences
Francesca Giampieri, Danila Cianciosi, Jose M. Alvarez-Suarez, Jose L. Quiles, Tamara Y. Forbes-Hernandez, Maria D. Navarro-Hortal, Michele Machi, Ramon del Jesus Pali Casanova, Julio Cesar Martinez Espinosa, Xiumin Chen, Di Zhang, Weibin Bai, Tian Lingmin, Bruno Mezzetti, Maurizio Battino, Yasmany Armas Diaz
Summary: Diets rich in plant-based foods have positive effects on overall well-being and help prevent non-communicable diseases. Fruits and vegetables are beneficial due to their micronutrient content, including vitamins, minerals, and polyphenols like anthocyanins. This commentary discusses recent scientific progress regarding anthocyanins, including their bioavailability, health effects, and relationship with gut microbiota.
JOURNAL OF BERRY RESEARCH
(2023)
Article
Remote Sensing
Imran Shafi, Muhammad Fawad Mazhar, Anum Fatima, Roberto Marcelo Alvarez, Yini Miro, Julio Cesar Martinez Espinosa, Imran Ashraf
Summary: This research proposes a real-time deep learning-based framework for identifying faulty components in the aerospace industry. The proposed AI system can perform inspection and defect detection, reducing the need for re-manufacturing and improving cost management. Ground and air tests indicate significant reductions in time delays and total cost.
Article
Energy & Fuels
Imran Shafi, Harris Khan, Muhammad Siddique Farooq, Isabel de la Torre Diez, Yini Miro, Juan Castanedo Galan, Imran Ashraf
Summary: This paper presents an artificial neural network (ANN)-based method to predict hybrid wind-solar resources and estimate power generation by correlating wind speed and solar radiation for real-time data. The proposed model uses temperature, humidity, air pressure, solar radiation, optimum angle, and target values of known wind speeds, solar radiation, and optimum angle for optimization. Experimental results show the effectiveness of the proposed approach in predicting wind speed, solar radiation, and optimum angle.
Article
Multidisciplinary Sciences
Ali Raza, Furqan Rustam, Hafeez Ur Rehman Siddiqui, Isabel de la Torre Diez, Imran Ashraf
Summary: Microbe organisms make up a significant portion of the earth's living matter, and they also inhabit the human body. These microbes pose health threats and can lead to various diseases in humans. This study aims to predict microbe organisms in the human body through an automated approach. A novel hybrid microbes classifier (HMC) based on decision tree and extra tree classifiers using voting criteria is proposed. The HMC approach achieves high accuracy, geometric mean score, precision score, and Cohen Kappa score, outperforming existing models. The research helps microbiologists accurately identify microbe organisms and prevent diseases through early detection.
Article
Medicine, General & Internal
Hafeez-Ur-Rehman Siddiqui, Ali Raza, Adil Ali Saleem, Furqan Rustam, Isabel de la Torre Diez, Daniel Gavilanes Aray, Vivian Lipari, Imran Ashraf, Sandra Dudley
Summary: Chronic obstructive pulmonary disease (COPD) is a common cause of mortality globally, and early detection is crucial. This study proposes a novel framework using artificial intelligence techniques and ultra-wideband (UWB) radar to detect COPD patients accurately with a 100% accuracy rate. The findings suggest that this framework has the potential to save lives by identifying COPD patients at an early stage.
Article
Multidisciplinary Sciences
Mario Martinez-Zarzuela, Javier Gonzalez-Alonso, Miriam Anton-Rodriguez, Francisco J. Diaz-Pernas, Henning Muller, Cristina Simon-Martinez
Summary: This article introduces the VIDIMU dataset, which aims to provide affordable patient gross motor tracking solutions for daily life activities recognition and kinematic analysis. The dataset is innovative in terms of its clinical relevance, combined utilization of affordable video and custom sensors, and the implementation of state-of-the-art tools for multimodal data processing. The validation confirms that a minimally disturbing acquisition protocol, performed according to real-life conditions, can provide a comprehensive picture of human joint angles during daily life activities.
Article
Medicine, General & Internal
Samra Shahzadi, Naveed Anwer Butt, Muhammad Usman Sana, Inaki Elio Pascual, Mercedes Briones Urbano, Isabel de la Torre Diez, Imran Ashraf
Summary: This study used independent component analysis to investigate the impact of Alzheimer's disease on different brain regions at different stages. Machine learning algorithms were used to categorize the stages of the disease. The study found that certain regions were impacted in all stages, and AdaBoost algorithm achieved excellent classification results.
Article
Medicine, General & Internal
Hafeez Ur Rehman Siddiqui, Adil Ali Saleem, Muhammad Amjad Raza, Santos Gracia Villar, Luis Alonso Dzul Lopez, Isabel de la Torre Diez, Furqan Rustam, Sandra Dudley
Summary: This study presents a novel approach for classifying lower limb disorders, specifically focusing on the knee, hip, and ankle. By utilizing gait analysis and PoseNet feature extraction, the research effectively identifies and categorizes these disorders. The proposed methodology shows potential in enhancing the diagnosis and treatment of lower limb disorders.
Review
Health Care Sciences & Services
Antonio Ferreras, Sandra Sumalla-Cano, Rosmeri Martinez-Licort, Inaka Elio, Kilian Tutusaus, Thomas Prola, Juan Luis Vidal-Mazon, Benjamin Sahelices, Isabel de la Torre Diez
Summary: Obesity and overweight are on the rise due to sedentary lifestyles and unhealthy diets. Machine learning (ML) has proved to be beneficial in the health sector, particularly in the development of algorithms and models for nutritionists and dieticians. A systematic review using the PRISMA protocol was conducted, resulting in the selection of 17 articles that applied ML and DL in disease prediction, treatment strategies, and personalized nutrition improvement. While DL was expected to yield better results, traditional methods remain more commonly used, with varying positive outcomes influenced more by transformed databases than the chosen AI paradigm. In conclusion, this compilation provides important insight into the application of ML in the field, highlighting its advantages over traditional statistics in terms of data modeling.
JOURNAL OF MEDICAL SYSTEMS
(2023)
Review
Computer Science, Information Systems
Chaudhary Hamza Rashid, Imran Shafi, Jamil Ahmad, Ernesto Bautista Thompson, Manuel Masias Vergara, Isabel de la Torre Diez, Imran Ashraf
Summary: Software cost and effort estimation is a significant task in software engineering, as accurate estimation is crucial for project success. This literature review investigates recent trends in published articles and proposes directions for improving estimation techniques.