Research on medical small sample data classification based on SMOTE and gcForest by Wenchang LIU, Yun WEI, Haoxuan YUAN, Yue GAO

“…Aiming at the problem of poor classification performance in traditional machine learning models caused by shallow model structure and complex data characteristics in small medical sample data, an combine multi- grained improved cascade forest (cgicForest) model was proposed.It enhances the representation learning ability of the model by adding random sampling into the multi-grained scanning and optimizing the transformation features.It also enhances the model's classification ability by updating the cascade forest’s hierarchical structure.Considering category imbalance problems in datasets, the safe-borderline-SMOTE (SBS) algorithm was proposed to dynamic interpolate around the few class samples belonging to the safety boundary, which can improve the quality of training data.The cgicForest was applied for training and learning, thus the SBS-cgicForest classification model was obtained which can support imbalanced medical small samples data.The model is used on three medical datasets for classification experiments.The results show that the performance indexes of the cgicForest model in the classification of medical small sample data with complex characteristics have increased by 4.1～5.4 percentage points, compared with the multi-grained cascade forest (gcForest) model.The performance indexes have increase by 6.6～11.2 percentage points after the combination with SBS algorithm, the F₁ score was 2～2.5 percentage points higher than that obtained by traditional sampling methods.It provides a reference for solving the classification problem of small medical sample data, and includes support for internet of things applications in smart medical scenarios.…”
Get full text

Leveraging multiplexed metasurfaces for multi-task learning with all-optical diffractive processors by Behroozinia Sahar, Gu Qing

“…Diffractive Neural Networks (DNNs) leverage the power of light to enhance computational performance in machine learning, offering a pathway to high-speed, low-energy, and large-scale neural information processing. …”
Get full text

Knowledge Graph Analysis of Digital Emergency Management Research Based on CiteSpace Visualisation: Comparative Analysis of WOS and CNKI Databases by Rui Nan, Wenjun Zhu, Yejing Xiao

“…The former are information technology, artificial intelligence, and machine learning, whereas the latter are emergency decision making, scenario analysis, and public health.…”
Get full text

Forecasting of Ionospheric Total Electron Content Data Using Multivariate Deep LSTM Model for Different Latitudes and Solar Activity by Nayana Shenvi, Hassanali Virani

“…The performance of the LSTM model was validated by comparing it with the multilayer perceptron (MLP) machine learning algorithm using root mean square error (RMSE) and mean absolute error (MAE) as evaluation indices. …”
Get full text

Spelling correction with large language models to reduce measurement error in open-ended survey responses by Maxwell B. Allamong, Jongwoo Jeong, Paul M. Kellstedt

“…Then, to highlight the potential benefits and limitations of spelling correction we show improved out-of-sample prediction accuracy from a text-based machine learning classifier. Finally, we show a significantly larger degree of emotionality is captured in the spelling-corrected texts, though the size of this measure’s relationship with a known correlate in political interest remains relatively unchanged. …”
Get full text

Motor Bearing Failure Identification Using Multiple Long Short-Term Memory Training Strategies by Youcef ATMANI, Ammar Mesloub, Said Rechak

“…In the context of condition-based maintenance of rotating machines in manufacturing systems, the early diagnosis of possible faults related to rolling elements of the bearing is mainly based on techniques from artificial intelligence, namely, Machine Learning (ML) and Deep Learning (DL). Approaches based on using Deep Learning methods have been the most coveted in recent years. …”
Get full text

Interpreting convolutional neural networks' low-dimensional approximation to quantum spin systems by Yilong Ju, Shah Saad Alam, Jonathan Minoff, Fabio Anselmi, Han Pu, Ankit Patel

“…In this work, we use methodologies from information theory, group theory and machine learning, to elucidate how CNN captures relevant physics of quantum systems. …”
Get full text

Crowdsourcing geographic information for terrorism-related disaster awareness and mitigation: perspectives and challenges by Michaelmary Chukwu, Xiao Huang, Siqin Wang, Di Yang, Xinyue Ye

“…Notably, we placed particular emphasis on the integration of Machine Learning (ML) algorithms in studying crowdsourced terrorism geoinformation to assess the current state of research and propose future directions. …”
Get full text

Unlocking autism’s complexity: the Move Initiative’s path to comprehensive motor function analysis by Ashley Priscilla Good, Elizabeth Horn

“…Despite advances in sensors, wearables, algorithms, machine learning, and agentic AI, autism research remains siloed, with many tools inaccessible to affected families and care teams. …”
Get full text

Multi-Planar Cervical Motion Dataset: IMU Measurements and Goniometer by Lee Keidan, Rawan Ibrahim, Evyatar Ohayon, Chaim G. Pick, Ella Been

“…The dataset herein serves as a benchmark for state-of-the-art machine learning models predicting head/neck position, analyzing smoothness of movements, measuring standard motion patterns, and calibrating drift based on movement comparisons.…”
Get full text

Role of Artificial Intelligence in Oral Cancer by Vidhya Rekha Umapathy, Prabhu Manickam Natarajan, Bhuminathan Swamikannu, Sabarinathan Jaganathan, Suba Rajinikanth, Vijayalakshmi Periyasamy

“…Artificial intelligence (AI) emerges as a forefront avenue in oral cancer (OC) therapeutics, engaged in providing solutions for diagnostic augmentation, treatment optimization, and prognostic delineation. Machine learning paradigms, encompassing supervised and unsupervised learning, afford meticulous classification and pattern identification from multifarious clinical and histopathological datasets. …”
Get full text

Efficient anomaly detection in tabular cybersecurity data using large language models by Xiaoyong Zhao, Xingxin Leng, Lei Wang, Ningning Wang, Yanqiong Liu

“…While traditional machine learning and deep learning methods have shown some success, they continue to face significant challenges in terms of generalization. …”
Get full text

Ontology-based prompt tuning for news article summarization by A. R. S. Silva, Y. H. P. P. Priyadarshana

“…Despite the progress in natural language processing (NLP) and machine learning, existing methods often rely on extractive summarization, which lacks the ability to generate coherent and contextually rich summaries. …”
Get full text

Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency by Chen Qiu, Ziang Wu, Haoda Wang, Qinglin Yang, Yu Wang, Chunhua Su

“…Federated Learning (FL) is a distributed machine-learning paradigm that enables models to be trained across multiple decentralized devices or servers holding local data without transferring the raw data to a central location. …”
Get full text

Intelligenza artificiale in medicina: alcune risposte – significative, ma parziali – offerte dal codice di deontologia medica (in materia di non discriminazione, consenso informato... by Paolo Zuddas

“…In particolare, si intende evidenziare come il ricorso a sistemi di AI medica: aumenti il rischio di operare discriminazioni nell’erogazione delle prestazioni sanitarie, in conseguenza dell’impiego, nell’addestramento dei sistemi di machine learning, di dati distorti e di dati incompleti; ponga in crisi l’istituto del consenso informato, stante la necessità di fornire informazioni complete concernenti anche le logiche di funzionamento dei sistemi informatici eventualmente coinvolti nell’attività diagnostica o terapeutica, a fronte delle note forme di opacità dei sistemi di AI; trasformi progressivamente il rapporto di cura, con ricadute destinate ad incidere sia sulla natura delle valutazioni cliniche sia sul ruolo del medico, chiamato ad operare sempre più come intermediario tra il paziente e il sistema informatico. …”
Get full text

Active learning-assisted directed evolution by Jason Yang, Ravi G. Lal, James C. Bowden, Raul Astudillo, Mikhail A. Hameedi, Sukhvinder Kaur, Matthew Hill, Yisong Yue, Frances H. Arnold

“…Here, we present Active Learning-assisted Directed Evolution (ALDE), an iterative machine learning-assisted DE workflow that leverages uncertainty quantification to explore the search space of proteins more efficiently than current DE methods. …”
Get full text

Body Surface Potential Mapping: A Perspective on High‐Density Cutaneous Electrophysiology by Ruben Ruiz‐Mateos Serrano, Dario Farina, George G. Malliaras

“…To mitigate this, two strategies are outlined: observational transformations that reconstruct signal sources for intuitive comprehension, and machine learning‐driven diagnostics. BSP mapping offers significant advantages in cutaneous electrophysiology with respect to classic electrophysiological recordings and is expected to expand into broader clinical domains in the future.…”
Get full text

Physiology-informed regularisation enables training of universal differential equation systems for biological applications. by Max de Rooij, Balázs Erdős, Natal A W van Riel, Shauna D O'Donovan

“…On the other hand, data-driven approaches such as machine learning models require large volumes of data to produce generalisable models. …”
Get full text

Learning From High-Cardinality Categorical Features in Deep Neural Networks by Mustafa Murat Arat

“…Some machine learning algorithms expect the input variables and the output variables to be numeric. …”
Get full text

Customer segmentation in the digital marketing using a Q-learning based differential evolution algorithm integrated with K-means clustering. by Guanqun Wang

“…Furthermore, four widely recognized machine learning methods are employed to classify the clustering results, achieving over 95% classification accuracy on the test set. …”
Get full text