Machine learning with applications最新文献

{"title":"Enhanced synthesis of passively heard speech from electrocorticography signals using image-to-image spectrogram translation","authors":"Hongsang Lee ,&nbsp;Jihun Hwang ,&nbsp;Kyungjun Kim ,&nbsp;Gyuwon Lee ,&nbsp;Chun Kee Chung ,&nbsp;Chang-Hwan Im","doi":"10.1016/j.mlwa.2025.100805","DOIUrl":"10.1016/j.mlwa.2025.100805","url":null,"abstract":"<div><div>Speech synthesis from neural signals offers a promising avenue for restoring communication in individuals with speech impairments. Recent deep learning advances have improved decoding of neural activity into intelligible speech, yet further enhancement is required to improve the quality of synthesized speech. Here, we investigate whether an image-to-image translation approach can further refine Mel spectrograms synthesized from electrocorticography (ECoG) signals recorded while participants passively listened to spoken sentences. ECoG data were collected from volunteers performing an auditory speech perception task. A three-layer bidirectional long short-term memory (Bi-LSTM) network was first trained to predict Mel-spectrogram features from neural signals. Comparison with the Conformer model indicated that Bi-LSTM was more effective as the initial synthesis model under our limited data conditions. To further enhance the quality of the Bi-LSTM-synthesized Mel spectrograms, we applied Pix2pixHD, a high-resolution conditional GAN, as a post-processing module. The impact of Pix2pixHD was evaluated using Log-Spectral Distance (LSD), Scale-Invariant Signal-to-Distortion Ratio (SI-SDR), and Short-Time Objective Intelligibility (STOI) comparing outputs against the original ground truth. Furthermore, subjective listening tests (2AFC similarity judgment) were conducted to assess perceptual improvements. Across objective metrics, Pix2pixHD post-processing yielded consistent improvements in spectral fidelity, waveform similarity, and estimated intelligibility (lower LSD, higher SI-SDR and STOI), and subjective tests confirmed significantly enhanced perceived similarity to the original speech. These gains were supported by non-parametric significance testing (Wilcoxon signed-rank test, <em>p</em> &lt; 0.005). The results indicate that high-resolution image-to-image translation is an effective vehicle to refine neural signal-based speech synthesis, complementing sequence models and improving the overall perceived quality of the synthesized speech.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100805"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145748780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-domain convergence of generative models: From biomedical to astronomical applications","authors":"Hajer Ghodhbani ,&nbsp;Suvendi Rimer ,&nbsp;Khmaies Ouahada ,&nbsp;Adel M. Alimi","doi":"10.1016/j.mlwa.2026.100841","DOIUrl":"10.1016/j.mlwa.2026.100841","url":null,"abstract":"<div><div>This paper investigates the convergence of generative modeling techniques across diverse image analysis tasks by examining their application in two data-intensive scientific domains: biomedical imaging and astronomy. In these two domains, which tend to be scientifically distinct due to their size and aims, they share common challenges, including noise corruption, limited availability of annotated data, and the demand for high-fidelity image reconstruction. This study provides a critical review of the various variants of generative models, with a particular focus on cross-domain applications. Unlike existing surveys that predominantly focus on a single discipline, this study emphasises the transferability and adaptability of generative models across biomedical and astronomical imaging. The proposed review highlights the potential offered by generative models, particularly Generative Adversarial Networks (GANS), in enhancing data generation, image restoration, and analysis in both biomedical and astronomical studies.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100841"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal information fusion for financial forecasting via cross-attention and calibrated uncertainty","authors":"Josué Bustarviejo,&nbsp;Carlos Bousoño-Calzón","doi":"10.1016/j.mlwa.2026.100840","DOIUrl":"10.1016/j.mlwa.2026.100840","url":null,"abstract":"<div><div>Forecasting financial markets requires synthesizing heterogeneous information sources such as historical prices, company indicators, and unstructured news, whose interactions are nonlinear and regime dependent. We investigate a cross-attention transformer framework that fuses these modalities for probabilistic financial forecasting with calibrated uncertainty. We propose a framework that anchors fusion on Chronos-T5, a transformer pretrained on large-scale time series and used here as a frozen encoder for market dynamics. Parameter-efficient projection layers map company-level indicators and daily news embeddings into a shared representation space, while bidirectional cross-attention learns how to align and weight the different sources. We evaluate the approach on daily EUR/USD forecasting, with additional experiments across currency pairs and market regimes. The multimodal model consistently outperforms autoregressive and deep learning baselines in point prediction, as measured by mean squared error and Diebold–Mariano tests, and delivers sharper probabilistic forecasts according to the continuous ranked probability score (CRPS), weighted interval score (WIS), and empirical coverage. Raw predictive distributions tend to be overconfident, but a post-hoc split conformal recalibration restores nominal coverage and improves interval quality without retraining the backbone. From a soft computing perspective, the system combines approximate Bayesian inference via Monte Carlo dropout with distribution-free calibration, within a structured cross-modal fusion architecture that improves the reliability and interpretability of multimodal financial forecasts.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100840"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Conformalized classifiers with reject option","authors":"Ulf Johansson,&nbsp;Cecilia Sönströd","doi":"10.1016/j.mlwa.2026.100838","DOIUrl":"10.1016/j.mlwa.2026.100838","url":null,"abstract":"<div><div>In data-driven decision support, predictive models built using machine learning aid in making informed decisions. In this context, models with a reject option may refrain from making predictions for certain instances. Accurately assessing the trade-off between predictive performance and throughput requires the ability to estimate performance at different rejection levels in advance. In this paper, we demonstrate how conformal prediction can be used for this purpose. Under exchangeability, the proposed conformalized classifiers can perfectly estimate accuracy or precision for any rejection level. In an empirical investigation using 41 publicly available datasets, the conformalized classifiers with a reject option are shown to clearly outperform probabilistic predictors calibrated with state-of-the-art techniques.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100838"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing marine mammal monitoring: Large-scale UAV delphinidae datasets and robust motion tracking for group size estimation","authors":"Leonardo Viegas Filipe ,&nbsp;João Canelas ,&nbsp;Mário Vieira ,&nbsp;Francisco Correia da Fonseca ,&nbsp;André Cid ,&nbsp;Joana Castro ,&nbsp;Inês Machado","doi":"10.1016/j.mlwa.2025.100808","DOIUrl":"10.1016/j.mlwa.2025.100808","url":null,"abstract":"<div><div>Reliable estimates of dolphin abundance are essential for conservation and impact assessment, yet manual analysis of aerial surveys is time-consuming and difficult to scale. This paper presents an end-to-end pipeline for automatic dolphin counting from unmanned aerial vehicle (UAV) video that combines modern object detection and multi-object tracking. We construct a large detection dataset of 64,705 images with 225,305 dolphin bounding boxes and a tracking dataset of 54,274 frames with 207,850 boxes and 603 unique tracks, derived from UAV line-transect surveys. Using these data, we train a YOLO11-based detector that achieves a precision of approximately 0.93 across a range of sea states. For tracking, we adopt BoT-SORT and tune its parameters with a genetic algorithm using a multi-metric objective, reducing ID fragmentation by about 29% relative to default settings. Recent YOLO-based cetacean detectors trained on UAV imagery of beluga whales report precision/recall around 0.92/0.92 for adults and 0.94/0.89 for calves, but rely on DeepSORT tracking whose MOTA remains below 0.5 and must be boosted to roughly 0.7 with post-hoc trajectory post-processing. In this context, our pipeline offers competitive detection performance, substantially larger and fully documented detection and tracking benchmarks, and GA-optimized tracking without manual post-processing. Applied to dolphin group counting, the full pipeline attains a mean absolute error of 1.24 on a held-out validation set, demonstrating that UAV-based automated counting can support robust, scalable monitoring of coastal dolphin populations.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100808"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benchmarking a time-series foundation model (TimeGPT) for real-world forecasting applications","authors":"Xiao Zhang ,&nbsp;Srinath Sridharan ,&nbsp;Nur Hakim Bin Zahrin ,&nbsp;Narayan Venkataraman ,&nbsp;Siang Hiong Goh","doi":"10.1016/j.mlwa.2025.100801","DOIUrl":"10.1016/j.mlwa.2025.100801","url":null,"abstract":"<div><div>Accurate forecasting of hospital demand is essential for operational resilience, yet traditional statistical and machine learning approaches often require extensive feature engineering and tuning, limiting adoption in resource-constrained environments. Foundation models for time-series forecasting offer the potential for robust, zero-shot performance across domains. This study evaluates the feasibility of TimeGPT, a general-purpose time-series foundation model, for forecasting daily Emergency Department (ED) arrivals.</div><div>We benchmarked TimeGPT against Seasonal Autoregressive Integrated Moving Average (SARIMAX), Prophet, and XGBoost under univariate and multivariate configurations. The experimental design simulated operational constraints by limiting the training window to 30 days and using a rolling forecast over a 60-day holdout period. Forecast accuracy was assessed using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and directional accuracy.</div><div>TimeGPT consistently ranked among the top-performing models. In the univariate setting, it achieved a MAPE of 7.7% and directional accuracy of 75%, comparable to or exceeding traditional models with extensive feature engineering. TimeGPT required no model-specific tuning and maintained accuracy without exogenous features such as weather or calendar variables. SARIMAX achieved the best results in the temporal-plus-weather configuration (MAPE 7.0%, RMSE 31.0) but required substantially more configuration. TimeGPT recorded zero large-error days (&gt;30% deviation), while SARIMAX had 5 such days, underscoring the trade-off between accuracy and robustness.</div><div>This benchmark demonstrates that foundation models can deliver accurate, reliable forecasts in healthcare operations with minimal data preparation. TimeGPT’s zero-shot capability highlights its potential as a scalable solution for diverse operational forecasting challenges.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100801"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel hybrid model of flying geese optimization and attention-LSTM for predicting survival outcomes in clear cell renal cell carcinoma","authors":"Cheng-Hong Yang ,&nbsp;Tin-Ho Cheung ,&nbsp;Yi-Ling Chen ,&nbsp;Sin-Hua Moi ,&nbsp;Li-Yeh Chuang","doi":"10.1016/j.mlwa.2026.100846","DOIUrl":"10.1016/j.mlwa.2026.100846","url":null,"abstract":"<div><div>Clear Cell Renal Cell Carcinoma (ccRCC) is the most aggressive and metastatic subtype of renal cell carcinoma and also the type with the highest mortality rate. To enhance survival prediction accuracy and facilitate informed clinical decision-making, this study presents a hybrid model that combines the Flying Geese Optimization Algorithm (FGOA) with an attention-based Long Short-Term Memory (A-LSTM) network. The proposed framework is trained and evaluated using data from the Cancer Genome Atlas Kidney Clear Cell Carcinoma (TCGA-KIRC) database. The feature selection process employed seven representative optimization algorithms covering evolutionary, swarm intelligence, and bio-inspired paradigms. The selected features were then analyzed using the attention-based A-LSTM network to predict survival outcomes in patients with ccRCC. Evaluation metrics for model performance included accuracy, precision, recall, and F1 score. The results showed that the FGOA-A-LSTM model performed best, with an accuracy of 80.8%, precision of 81.5%, recall of 86.9%, and F1 score of 84.1%, outperforming the other models. This result also indicates that on imbalanced datasets, the F1 score may be higher than the accuracy. Furthermore, Cox proportional hazards regression analysis showed that survival outcomes were significantly correlated with factors such as gender, tumor stage, previous treatment, and treatment method. This study introduces an innovative FGOA-A-LSTM framework that improves survival prediction in ccRCC. By integrating optimization-driven feature selection with an attention-enhanced deep learning architecture, the work makes a contribution to improving clinical risk assessment.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100846"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced Heart disease prediction using LLM ranked feature selection, Dynamic custom Kernel","authors":"Nikesh P.L. ,&nbsp;Sebastian Terence ,&nbsp;Anishin Raj ,&nbsp;Jude Immaculate ,&nbsp;Deepak Mishra","doi":"10.1016/j.mlwa.2026.100860","DOIUrl":"10.1016/j.mlwa.2026.100860","url":null,"abstract":"<div><div>Heart disease, a major cause of death worldwide, accounts for millions of deaths each year. This makes it critical to detect heart disease at an earlier stage so that a treatment plan, including medications and counseling, can be started. Machine learning (ML) algorithms trained on large datasets have made it possible to predict heart disease more effectively. Traditional machine learning approaches provide statistical correlations, but often lack explicit integration of clinical knowledge, which limits their usefulness in real-world scenarios. This paper investigates the use of Large Language Model (LLM) combined with Retrieval-Augmented Generation (RAG) to derive clinically grounded feature relevance based on medical guidelines. A curated corpus of medical guidelines and practice protocols from internationally approved organizations was used to train the RAG pipeline. The features were ranked using LLM powered by RAG, and themost important features were selected and used in a Support Vector Machine (SVM) with a custom kernel. A custom formulation combining linear and non linear functions were explored as an auxiliary modeling component. This enables the model to keep the clinical importance of the features, linear transparency and also captures complex interactions using a polynomial function. This approach is evaluated on the UCI Heart Disease dataset, which includes data from Cleveland, Hungary, Switzerland, and VA Medical Center in Long Beach. This study conducted in two parts one using only Cleveland alone and a full set of data using all 4 regions. This integration of statistical learning with LLM driven reasoning supports cardiovascular risk assessment in a clinically informed manner. This approach helps to identify clinically relevant features for the learning process. On the Cleveland dataset the model achieved an accuracy of 95%, an F1 score of 0.936, and an AUC-ROC of 0.973, but it was comparable with traditional models and without weighted kernel due to the size of the data. When applied on the combined dataset, using the entire UCI dataset, the model achieved an accuracy of 93.3%, F1 score 0.923 and AUC-ROC of 0.961. Statistical testing showed that the weighted and unweighted kernels performed similarly, suggesting that the primary contribution arises from clinically guided feature selection rather than kernel weighting. The combination of statistical methods and reasoning from LLM models improves both the effectiveness and clarity of predictions. This process helps develop clinically informed AI systems for cardiovascular risk assessment. This paper also includes a comparative study of logistic regression, decision tree, random forest, gradient boosting, and support vector machine with RBF, sigmoid, linear and polynomial kernels.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100860"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoding vision transformer variations for image classification: A guide to performance and usability","authors":"João Montrezol ,&nbsp;Hugo S. Oliveira ,&nbsp;Hélder P. Oliveira","doi":"10.1016/j.mlwa.2026.100844","DOIUrl":"10.1016/j.mlwa.2026.100844","url":null,"abstract":"<div><div>With the rise of Transformers, Vision Transformers (ViTs) have become a new standard in visual recognition. This has led to the development of numerous architectures with diverse designs and applications. This survey identifies 22 key ViT and hybrid CNN–ViT models, along with 5 top Convolutional Neural Network (CNN) models. These were selected based on their new architecture, relevance to benchmarks, and overall impact. The models are organised using a defined taxonomy formed by CNN-based, pure Transformer-based, and hybrid architectures. We analyse their main components, training methods, and computational features, while assessing performance using reported results on standard benchmarks such as ImageNet and CIFAR, along with our training and fine-tuning evaluations on specific imaging datasets. In addition to accuracy, we look at real-world deployment issues by analysing the trade-offs between accuracy and efficiency in embedded, mobile, and clinical settings. The results indicate that modern CNNs are still very competitive in limited-resource environments, while advanced ViT variants perform well after large-scale pretraining, especially in areas with high variability. Hybrid CNN–ViT architectures, on the other hand, tend to offer the best balance between accuracy, data efficiency, and computational cost. This survey establishes a consolidated benchmark and reference framework for understanding the evolution, capabilities, and practical applicability of contemporary vision architectures.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100844"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-driven detection of tiny pests in foliage: Integrating image processing and deep learning","authors":"Lucía Baeza-Moreno ,&nbsp;Pedro Blanco-Carmona ,&nbsp;Eduardo Hidalgo-Fort ,&nbsp;Rubén Martín-Clemente ,&nbsp;Ramón González-Carvajal","doi":"10.1016/j.mlwa.2025.100834","DOIUrl":"10.1016/j.mlwa.2025.100834","url":null,"abstract":"<div><div>We present a novel computer vision method for detecting insect pests on plant and tree leaves under real-world conditions, combining deep learning with classical image processing techniques. Detecting small, sparsely distributed, or camouflaged insects is challenging, as current state-of-the-art object detection methods, primarily designed for larger objects, often overlook them. Our approach to this problem is twofold. First, we employ a deep learning model to analyze suspicious leaves for anomalies (a task well suited to deep learning). However, since deep models struggle with tiny objects in complex backgrounds, we complement them with conventional image processing to pre-identify potentially infested foliage, guiding the model toward relevant areas and mitigating its limitations. This combined strategy proves effective and competitive with other methods across diverse datasets and real-world scenarios. Furthermore, we also conduct a detailed analysis to interpret the model’s predictions, strengthening confidence in its effectiveness.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"23 ","pages":"Article 100834"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145924638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}