Hasil untuk "machine learning"

Zixiang Ye, Xuewen Chen, Lvxin Qian et al.

Traditional water quality monitoring methods are limited in providing timely chlorophyll-<i>a</i> (Chl-<i>a</i>) assessments in small inland reservoirs. This study presents a rapid Chl-<i>a</i> retrieval approach based on a cooperative unmanned aerial vehicle–uncrewed surface vessel (UAV–USV) framework that integrates UAV hyperspectral imaging, machine learning algorithms, and synchronized USV in situ sampling. We carried out a three-day cooperative monitoring campaign in the Longhu Reservoir of Fujian Province, during which high-frequency hyperspectral imagery and water samples were collected. An innovative median-based correction method was developed to suppress striping noise in UAV hyperspectral data, and a two-step band selection strategy combining correlation analysis and variance inflation factor screening was used to determine the input features for the subsequent inversion models. Four commonly used machine-learning-based inversion models were constructed and evaluated, with the random forest model achieving the highest accuracy and stability across both training and testing datasets. The generated Chl-<i>a</i> maps revealed overall good water quality, with localized higher concentrations in weakly hydrodynamic zones. Overall, the cooperative UAV–USV framework enables synchronized data acquisition, rapid processing, and fine-scale mapping, demonstrating strong potential for fast-response and emergency water-quality monitoring in small inland drinking-water reservoirs.

Fatemeh Habibkhah, Mehrdad Moallem

Robert Rein

Arifin Fahmi, Wicaksono Ashari

Coastal areas are often threatened by natural and anthropogenic factors, causing instability and shoreline changes in the affected areas. Shoreline changes can be monitored with remote sensing techniques such as Synthetic Aperture Radar (SAR) data. The purpose of this research is to extract the coastline by segmenting the machine learning method and find out how far the machine learning model works to distinguish the water class and the land class. The method used in this research is the Support Vector Machine model to divide the water and land classes that will be utilized to obtain shoreline extracts from the model results, and evaluate the model by calculating the model accuracy. The overall accuracy results recorded in 2016 and 2023 are 99.5% and 99%, respectively, with Kappa Coefficients of 0.99018 and 0.98138. This study highlights the potential of SAR data and SVM methods in monitoring coastal dynamics and can serve as a reference for sustainable coastal management.

Dong Wang, Chunlai Chen, Christopher Findlay et al.

ABSTRACT This paper contributes a new paradigm for international agricultural development research. It uses machine learning techniques to aid expert diagnosis of development problems in conjunction with New Structural Economics (NSE) to analyse and design policies to enable effective rural transformation. It conducts a multi‐country, multi‐regional, multi‐level and multi‐dimensional analysis in Bangladesh, China, Indonesia, and Pakistan to identify stage segmentations of rural transformation and examine stagewise associate policies and applicable learnings across each dimension. By presenting structured stages of rural transformation, we provide guidance on designing dynamic comparative‐advantage‐adapting policies that are able to adapt at each stage. This analytical procedure can serve other relevant agricultural development studies.

Pablo Guillén, Enrique Frias-Martinez

Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by memory loss. While applying Machine Learning (ML) demands a certain level of expertise, which is often a barrier for healthcare professionals, automated machine learning (AutoML) significantly lowers this barrier. This study analyzes an AutoML tool (PyCaret) for AD classification and prediction. Two experiments were designed to evaluate its diagnostic and prognostic capabilities with AD, Mild cognitive impairment (MCI), and Normal Controls (NC). SHapley Additive exPlanations (SHAP) was used to explain the ML models. For diagnosis, it had an accuracy of 98.6% for NC vs AD, 91.3%, for NC vs MCI, 92.5% for MCI vs AD, and 89.5% for the multiclass NC vs MCI vs AD. Regarding the prognosis capabilities, prediction of future cognitive states four years after their initial visit produced an accuracy of 92.8% for NC vs AD, 82.7% for NC vs MCI, 90.2% for MCI vs AD, and 81.4% for NC vs MCI vs AD. These results are in range and, in some cases, improve the state of the art even when compared to deep learning solutions. They confirm the potential of AutoML tools to automate ML algorithm selection and tuning for a specific medical application.

Fernando Martinez-Martinez, David Roldán-Álvarez, Estefanía Martín-Barroso

The discussion in social networks is of general interest, but the extraction, curation and visualization of this information turns difficult for those without programming knowledge. In the framework of the project CSTrack, which studies the activities in Citizen Science, we present an easily accessible dashboard aimed to provide a platform for people of different levels of expertise and professionals. They can retrieve valuable information about the trends and topics inside Twitter with a standardized pipeline for analysis that provides a complete understanding of the state of the conversation in social networks. With this platform, we present an alternative to the lack of standardization in social networking analysis and also, we aim to palliate the insufficiency of replication of social network research.

Dae Hyun Lim, Yung-Kyun Noh, Byoung Kwan Son et al.

Abstract Cancer-associated fibroblasts promote tumor progression through growth facilitation, invasion, and immune evasion. This study investigated the impact of activated cancer-associated fibroblasts (aCAFs) on survival outcomes, immune response, and molecular pathways in distal bile duct (DBD) cancer. We analyzed 469 patients (418 from our cohort and 51 from The Cancer Genome Atlas) with DBD adenocarcinoma. aCAFs were evaluated using hematoxylin and eosin staining. We developed a machine learning-based survival prediction model incorporating aCAFs and clinicopathologic parameters. Additionally, we performed differential gene expression analysis, Disease Ontology analysis, gene set enrichment analysis, and in vitro drug screening of aCAFs-related genes. The presence of aCAFs significantly correlated with poor survival, advanced T and N stages, infiltrative growth pattern, lymphatic/perineural/adjacent organ invasion, and decreased tumor-infiltrating lymphocytes. aCAFs-related genes were associated with immune system functions, G protein-coupled receptor signaling, and metabolic conditions (diabetes, obesity, and abnormal C-peptide levels). In machine learning-based survival models, aCAFs emerged as a strong discriminator for survival prediction. In vitro drug screening revealed that refametinib suppressed the growth of DBD carcinoma cells expressing high levels of fibroblast activation protein-α. In conclusion, integration of machine learning and systems biology analyses identifies aCAFs as potential biomarkers for risk stratification and therapeutic targeting in DBD cancer.

Changhoon Lee, Sujung Park, Daeung Yoon et al.

IntroductionAccurate classification of seabed sediments is essential for marine spatial planning, resource management, and scientific research. While direct sampling yields precise sediment information, it is costly and spatially limited. Multibeam echo-sounding systems (MBES) offer broad coverage but lack detailed sediment characterization, creating a need for an integrated, data-driven approach.MethodsWe developed a machine-learning framework that fuses MBES backscatter data with limited seabed samples. Missing MBES values were first interpolated using a U-Net model to create a complete raster dataset. Advanced texture and spectral descriptors—Gray-Level Co-occurrence Matrix, Law’s texture filters, and discrete wavelet transforms—were extracted from the backscatter imagery. Five classifiers (Random Forest, Support Vector Machine, Deep Neural Network, Extreme Gradient Boosting, Light Gradient-Boosting Machine) were trained to predict four sediment classes (gravel, sand, clay, silt). To mitigate sample scarcity and class imbalance, a semi-supervised self-training loop iteratively added high-confidence pseudo-labels to the training set.ResultsField validation in the East Sea (Republic of Korea) showed that the Extreme Gradient Boosting model achieved the highest accuracy. Overall prediction accuracy increased from 60.81 % with the baseline workflow to 72.73 % after applying data interpolation, enhanced feature extraction, and self-training.DiscussionThe proposed combination of U-Net interpolation, multi-scale texture features, and semi-supervised learning significantly improves sediment classification where MBES data are incomplete and sediment samples are sparse. This integrated workflow demonstrates the potential of machine-learning techniques to advance seabed mapping and support informed marine resource management.

Yue Zheng, Xiaoming Jing, Yonggang Lin et al.

With the impact of global climate change and the urbanization process, the risk of urban flooding has increased rapidly, especially in developing countries. Real-time monitoring and prediction of flooding extent and drainage system are the foundation of effective urban flood emergency management. Therefore, this paper presents a rapid nowcasting prediction method of urban flooding based on data-driven and real-time monitoring. The proposed method firstly adopts a small number of monitoring points to deduce the urban global real-time water level based on a machine learning algorithm. Then, a data-driven method is developed to achieve dynamic urban flooding nowcasting prediction with real-time monitoring data and high-accuracy precipitation prediction. The results show that the average MAE and RMSE of the urban flooding and conduit system in the deduction method for water level are 0.101 and 0.144, 0.124 and 0.162, respectively, while the flooding depth deduction is more stable compared to the conduit system by probabilistic statistical analysis. Moreover, the urban flooding nowcasting method can accurately predict the flooding depth, and the R2 are as high as 0.973 and 0.962 of testing. The urban flooding nowcasting prediction method provides technical support for emergency flood risk management. HIGHLIGHTS A rapid nowcasting prediction method of urban flood based on data-driven and real-time monitoring.; The deduction model accurately estimates the global water depth.; The proposed urban flooding nowcasting model was observed to outperform the traditional machine learning model to predict.;

Bo Wen, Jian Chen, Tianqi Ding et al.

Abstract Osteosarcoma (OS) is the most common primary malignant tumour of the bone with high mortality. Here, we comprehensively analysed the hypoxia signalling in OS and further constructed novel hypoxia-related gene signatures for OS prediction and prognosis. This study employed Gene Set Enrichment Analysis (GSEA), Weighted correlation network analysis (WGCNA) and Least absolute shrinkage and selection operator (LASSO) analyses to identify Stanniocalcin 2 (STC2) and Transmembrane Protein 45A (TMEM45A) as the diagnostic biomarkers, which further assessed by Receiver Operating Characteristic (ROC), decision curve analysis (DCA), and calibration curves in training and test dataset. Univariate and multivariate Cox regression analyses were used to construct the prognostic model. STC2 and metastasis were devised to forge the OS risk model. The nomogram, risk score, Kaplan Meier plot, ROC, DCA, and calibration curves results certified the excellent performance of the prognostic model. The expression level of STC2 and TMEM45A was validated in external datasets and cell lines. In immune cell infiltration analysis, cancer-associated fibroblasts (CAFs) were significantly higher in the low-risk group. And the immune infiltration of CAFs was negatively associated with the expression of STC2 (P < 0.05). Pan-cancer analysis revealed that the expression level of STC2 was significantly higher in Esophageal carcinoma (ESCA), Head and Neck squamous cell carcinoma (HNSC), Kidney renal clear cell carcinoma (KIRC), Lung squamous cell carcinoma (LUSC), and Stomach adenocarcinoma (STAD). Additionally, the higher expression of STC2 was associated with the poor outcome in those cancers. In summary, this study identified STC2 and TMEM45A as novel markers for the diagnosis and prognosis of osteosarcoma, and STC2 was shown to correlate with immune infiltration of CAFs negatively.

Annisa Nasywa Atsilah, Trias Aditya Kurniawan Muhammad

Meningkatnya harga properti di kawasan perkotaan dipengaruhi oleh pesatnya urbanisasi di kawasan perkotaan. Pola spasial terkait nilai tanah dan properti yang kompleks akibat pembangunan gedung-gedung tinggi belum dipahami dengan baik. Secara umum, penilaian tanah dan properti dipengaruhi oleh aspek lokasi, lingkungan, dan fisik. Pembangunan yang terus berkembang menyebabkan perubahan spasial yang signifikan dalam dimensi vertikal. Faktor 2D yang saat ini digunakan tidak dapat mewakili perubahan informasi spasial pada dimensi vertikal. Oleh karena itu, penting untuk memperhitungkan faktor 3D dalam proses penilaian tanah dan properti. Penelitian ini bertujuan untuk menganalisis faktor 3D pada penilaian tanah dan properti sebagai dasar penentuan pajak dengan menerapkan metode Hedonic Price Modeling (HPM). Metode HPM dikembangkan untuk penilaian tanah dan properti 3D menggunakan regresi berganda dengan pembelajaran mesin (machine learning). Hasil dari penelitian, menunjukkan bahwa penambahan faktor 3D pada model memiliki pengaruh yang signifikan terhadap nilai tanah dan properti. Hal ini didukung oleh hasil validasi menggunakan uji independen t, yang menunjukkan bahwa tidak terdapat perbedaan secara signifikan antara rata-rata nilai pasar dan Nilai Jual Objek Pajak (NJOP). Selain itu, penyajian model kota LoD 1, dinilai efektif dalam menggambarkan pola distribusi spasial terkait klasifikasi Pajak Bumi dan Bangunan (PBB) yang tersebar di area studi. Pola yang tergambar dalam model kota tersebut dapat mempermudah pemangku kepentingan dalam memahami tren PBB dalam konteks spasial, sekaligus memudahkan dalam pengambilan keputusan terkait kebijakan pajak dan perencanaan kota.

Nathan K. Long, Robert Malaney, Kenneth J. Grant

Continuous-variable quantum key distribution (CV-QKD) shows potential for the rapid development of an information-theoretic secure global communication network; however, the complexities of CV-QKD implementation remain a restrictive factor. Machine learning (ML) has recently shown promise in alleviating these complexities. ML has been applied to almost every stage of CV-QKD protocols, including ML-assisted phase error estimation, excess noise estimation, state discrimination, parameter estimation and optimization, key sifting, information reconciliation, and key rate estimation. This survey provides a comprehensive analysis of the current literature on ML-assisted CV-QKD. In addition, the survey compares the ML algorithms assisting CV-QKD with the traditional algorithms they aim to augment, as well as providing recommendations for future directions for ML-assisted CV-QKD research.

L. Fortaner-Uyà, C. Monopoli, F. Calesella et al.

Introduction Every year at least one million people die by suicide, with major depressive disorder (MDD) being one of the major causes of suicide deaths. Current suicide risk assessments rely on subjective information, are time consuming, low predictive, and poorly reliable. Thus, finding objective biomarkers of suicidality is crucial to move clinical practice towards a precision psychiatry framework, enhancing suicide risk detection and prevention for MDD. Objectives The present study aimed at applying machine learning (ML) algorithms on both grey matter and white-matter voxel-wise data to discriminate MDD suicide attempters (SA) from non-attempters (nSA). Methods 91 currently depressed MDD patients (24 SA, 67 nSA) underwent a structural MRI session. T1-weighted images and diffusion tensor imaging scans were respectively pre-processed using Computational Atlas Toolbox 12 (CAT12) and spatial tract-based statistics (TBSS) on FSL, to obtain both voxel-based morphometry (VBM) and fractional anisotropy (FA) measures. Three classification models were built, entering whole-brain VBM and FA maps alone into a Support Vector Machine (SVM) and combining both modalities into a Multiple Kernel Learning (MKL) algorithm. All models were trained through a 5-fold nested cross-validation with subsampling to calculate reliable estimates of balanced accuracy, specificity, sensitivity, and area under the receiver operator curve (AUC). Results Models’ performances are summarized in Table 1.Table 1. Models’ performances. Input features Algorithm Specificity Sensitivity Balanced accuracy AUC VBM SVM 55.00% 50.00% 52.50% 0.55 FA SVM 72.00% 54.00% 63.00% 0.62 VBM and FA MKL 68.00% 54.00% 61.00% 0.58 Abbreviations: AUC, area under the receiver operator curve; FA, fractional anisotropy; VBM, voxel-based morphometry. Conclusions Overall, although overcoming the random classification accuracy (i.e., 50%), performances of all models classifying SA and nSA MDD patients were moderate, possibly due to the imbalanced numerosity of classes, with SVM on FA reaching the highest accuracy. Thus, future studies may enlarge the sample and add different features (e.g., functional neuroimaging data) to develop an objective and reliable predictive model to assess and hence prevent suicide risk among MDD patients. Disclosure of Interest None Declared

Dagoberto Castellanos-Nieves, Luis García-Forte

Automated machine learning (AutoML), which aims to facilitate the design and optimization of machine-learning models with reduced human effort and expertise, is a research field with significant potential to drive the development of artificial intelligence in science and industry. However, AutoML also poses challenges due to its resource and energy consumption and environmental impact, aspects that have often been overlooked. This paper predominantly centers on the sustainability implications arising from computational processes within the realm of AutoML. Within this study, a proof of concept has been conducted using the widely adopted Scikit-learn library. Energy efficiency metrics have been employed to fine-tune hyperparameters in both Bayesian and random search strategies, with the goal of enhancing the environmental footprint. These findings suggest that AutoML can be rendered more sustainable by thoughtfully considering the energy efficiency of computational processes. The obtained results from the experimentation are promising and align with the framework of Green AI, a paradigm aiming to enhance the ecological footprint of the entire AutoML process. The most suitable proposal for the studied problem, guided by the proposed metrics, has been identified, with potential generalizability to other analogous problems.

Li Gengluo, Jimenez Giorgos

When skin cells divide abnormally, it can cause a tumor or abnormal lymph fluid or blood. The masses appear benign and malignant, with the benign being limited to one area and not spreading, but some can spread throughout the body through the body’s lymphatic system. Skin cancer is easier to diagnose than other cancers because its symptoms can be seen with the naked eye. This makes us to provide an artificial intelligence-based methodology to diagnose this cancer with higher accuracy. This article proposes a new non-destructive testing method based on the AlexNet and Extreme Learning Machine network to provide better results of the diagnosis. The method is then optimized based on a new improved version of the Grasshopper optimization algorithm (GOA). Simulation of the proposed method is then compared with some different state-of-the-art methods and the results showed that the proposed method with 98% accuracy and 93% sensitivity has the highest efficiency.

Hajira Dambha-Miller, Glenn Simpson, Ralph K Akyea et al.

BackgroundMultiple long-term health conditions (multimorbidity) (MLTC-M) are increasingly prevalent and associated with high rates of morbidity, mortality, and health care expenditure. Strategies to address this have primarily focused on the biological aspects of disease, but MLTC-M also result from and are associated with additional psychosocial, economic, and environmental barriers. A shift toward more personalized, holistic, and integrated care could be effective. This could be made more efficient by identifying groups of populations based on their health and social needs. In turn, these will contribute to evidence-based solutions supporting delivery of interventions tailored to address the needs pertinent to each cluster. Evidence is needed on how to generate clusters based on health and social needs and quantify the impact of clusters on long-term health and costs. ObjectiveWe intend to develop and validate population clusters that consider determinants of health and social care needs for people with MLTC-M using data-driven machine learning (ML) methods compared to expert-driven approaches within primary care national databases, followed by evaluation of cluster trajectories and their association with health outcomes and costs. MethodsThe mixed methods program of work with parallel work streams include the following: (1) qualitative semistructured interview studies exploring patient, caregiver, and professional views on clinical and socioeconomic factors influencing experiences of living with or seeking care in MLTC-M; (2) modified Delphi with relevant stakeholders to generate variables on health and social (wider) determinants and to examine the feasibility of including these variables within existing primary care databases; and (3) cohort study with expert-driven segmentation, alongside data-driven algorithms. Outputs will be compared, clusters characterized, and trajectories over time examined to quantify associations with mortality, additional long-term conditions, worsening frailty, disease severity, and 10-year health and social care costs. ResultsThe study will commence in October 2021 and is expected to be completed by October 2023. ConclusionsBy studying MLTC-M clusters, we will assess how more personalized care can be developed, how accurate costs can be provided, and how to better understand the personal and medical profiles and environment of individuals within each cluster. Integrated care that considers “whole persons” and their environment is essential in addressing the complex, diverse, and individual needs of people living with MLTC-M. International Registered Report Identifier (IRRID)PRR1-10.2196/34405

Sambandh Bhusan Dhal, Muthukumar Bagavathiannan, Ulisses Braga-Neto et al.

With the recent advances in the field of alternate agriculture, there has been an ever-growing demand for aquaponics as a potential substitute for traditional agricultural techniques for improving sustainable food production. However, the lack of data-driven methods and approaches for aquaponic cultivation remains a challenge. The objective of this research is to investigate statistical methods to make inferences using small datasets for nutrient control in aquaponics to optimize yield. In this work, we employed the Density-Based Synthetic Minority Over-sampling TEchnique (DB-SMOTE) to address dataset imbalance, and ExtraTreesClassifer and Recursive Feature Elimination (RFE) to choose the relevant features. Synthetic data generation techniques such as the Monte-Carlo (MC) sampling techniques were used to generate enough data points and different feature engineering techniques were used on the predictors before evaluating the performance of kernel-based classifiers with the goal of controlling nutrients in the aquaponic solution for optimal growth.[27-35].

Anupama Jamwal, Shruti Jain

Machine learning is useful for pattern recognition, if allowed access to patient data, it can notice patterns that would be missed by human doctors, which could be used to predict if a person is at risk for a disease that would not have been anticipated by a doctor. In this paper, the authors have proposed an Empirical Riglit Wavelet Transform algorithm. In this algorithm, the authors have fused the filter banks of CT and MR images obtained from Ridgelet and Little wood Empirical Wavelet Transform. Four possible combinations were used for the fusion. Image boundaries were evaluated as performance parameters. With that parameters helps in understanding the small elements and details from given CT and MR images. The objective of this paper is to classify and extract specific patterns in the images using different combinations of CT and MR by fusing them. The proposed algorithm is validated via filter banks obtained for fused CT-MT images using the same techniques.

Zichen Fan