Search Results (2,289)

Deep learning has shown remarkable success in medical image analysis over the last decade; however, many contributions focused on supervised methods which learn exclusively from labeled training samples. Acquiring expert-level annotations in large quantities is time-consuming and costly, even more so in medical image segmentation, where annotations are required on a pixel level and often in 3D. As a result, available labeled training data and consequently performance is often limited. Frequently, however, additional unlabeled data are available and can be readily integrated into model training, paving the way for semi- or self-supervised learning (SSL). In this work, we investigate popular SSL strategies in more detail, namely Transformation Consistency, Student–Teacher and Pseudo-Labeling, as well as exhaustive combinations thereof. We comprehensively evaluate these methods on two 2D and 3D cardiac Magnetic Resonance datasets (ACDC, MMWHS) for which several different multi-compartment segmentation labels are available. To assess performance in limited dataset scenarios, different setups with a decreasing amount of patients in the labeled dataset are investigated. We identify cascaded Self-Supervision as the best methodology, where we propose to employ Pseudo-Labeling and a self-supervised cascaded Student–Teacher model simultaneously. Our evaluation shows that in all scenarios, all investigated SSL methods outperform the respective low-data supervised baseline as well as state-of-the-art self-supervised approaches. This is most prominent in the very-low-labeled data regime, where for our proposed method we demonstrate $10.17\%$ and $6.72\%$ improvement in Dice Similarity Coefficient (DSC) for ACDC and MMWHS, respectively, compared with the low-data supervised approach, as well as $2.47\%$ and $7.64\%$ DSC improvement, respectively, when compared with related work. Moreover, in most experiments, our proposed method is able to greatly decrease the performance gap when compared to the fully supervised scenario, where all available labeled samples are used. We conclude that it is always beneficial to incorporate unlabeled data in cardiac MRI segmentation whenever it is present. Full article

The rapid growth of e-commerce has made it increasingly difficult for users to select appropriate products due to the overwhelming amount of available information. Although many platforms, such as Amazon and Rakuten, encourage users to leave reviews, effectively utilizing this information for personalized recommendations remains a challenge. To address this issue, we propose a multi-task product recommender system that supports both new users without purchase histories and existing users with interaction records. For new users without purchase histories, we introduce a ranking-based method that combines three market-oriented features: sales volume, sales period, and user satisfaction. User satisfaction is quantified using sentiment analysis of product reviews. These three factors are integrated into a composite score to identify products with a strong market presence and positive customer feedback. For existing users, we developed an enhanced neural collaborative filtering (NCF) method that incorporates a product bias factor. This model, named bias neural collaborative filtering (BNCF), utilizes multilayer perceptrons to learn latent user–product interactions while also capturing item popularity bias. We evaluated the proposed approaches using a real-world dataset from Rakuten. The results show that our multi-task system effectively improves recommendation quality for users in both cold-start and data-rich scenarios. Full article

This study evaluates the performance and energy trade-offs of three popular data processing libraries—Pandas, PySpark, and Polars—applied to GreenNav, a CO₂ emission prediction pipeline for urban traffic. GreenNav is an eco-friendly navigation app designed to predict CO₂ emissions and determine low-carbon routes using a hybrid CNN-LSTM model integrated into a complete pipeline for the ingestion and processing of large, heterogeneous geospatial and road data. Our study quantifies the end-to-end execution time, cumulative CPU load, and maximum RAM consumption for each library when applied to the GreenNav pipeline; it then converts these metrics into energy consumption and CO₂ equivalents. Experiments conducted on datasets ranging from 100 MB to 8 GB demonstrate that Polars in lazy mode offers substantial gains, reducing the processing time by a factor of more than twenty, memory consumption by about two-thirds, and energy consumption by about 60%, while maintaining the predictive accuracy of the model (R² ≈ 0.91). These results clearly show that the careful selection of data processing libraries can reconcile high computing performance and environmental sustainability in large-scale machine learning applications. Full article

Rust’s growing popularity in high-integrity systems requires automated vulnerability detection in order to maintain its strong safety guarantees. Although Rust’s ownership model and compile-time checks prevent many errors, sometimes unexpected bugs may occasionally pass analysis, underlining the necessity for automated safe and unsafe code detection. This paper presents Rust-IR-BERT, a machine learning approach to detect security vulnerabilities in Rust code by analyzing its compiled LLVM intermediate representation (IR) instead of the raw source code. This approach offers novelty by employing LLVM IR’s language-neutral, semantically rich representation of the program, facilitating robust detection by capturing core data and control-flow semantics and reducing language-specific syntactic noise. Our method leverages a graph-based transformer model, GraphCodeBERT, which is a transformer architecture pretrained model to encode structural code semantics via data-flow information, followed by a gradient boosting classifier, CatBoost, that is capable of handling complex feature interactions—to classify code as vulnerable or safe. The model was evaluated using a carefully curated dataset of over 2300 real-world Rust code samples (vulnerable and non-vulnerable Rust code snippets) from RustSec and OSV advisory databases, compiled to LLVM IR and labeled with corresponding Common Vulnerabilities and Exposures (CVEs) identifiers to ensure comprehensive and realistic coverage. Rust-IR-BERT achieved an overall accuracy of 98.11%, with a recall of 99.31% for safe code and 93.67% for vulnerable code. Despite these promising results, this study acknowledges potential limitations such as focusing primarily on known CVEs. Built on a representative dataset spanning over 2300 real-world Rust samples from diverse crates, Rust-IR-BERT delivers consistently strong performance. Looking ahead, practical deployment could take the form of a Cargo plugin or pre-commit hook that automatically generates and scans LLVM IR artifacts during the development cycle, enabling developers to catch vulnerabilities at an early stage in the development cycle. Full article

Over the past few decades, lithium-ion batteries (LIBs) have gained significant attention due to their inherent potential for environmental sustainability and unparalleled energy storage efficiency. Meanwhile, polymer electrolytes have gained popularity in several fields due to their ability to adapt to various battery geometries, enhanced safety features, greater thermal stability, and effectiveness in reducing dendrite growth on the anode. However, their relatively low ionic conductivity compared to liquid electrolytes has limited their application in high-performance devices. This limitation has led to recent studies revolving around the development of poly(ionic liquids) (PILs), particularly imidazolium-mediated polymer backbones as novel electrolyte materials, which can increase the conductivity with fine-tuning structural benefits, while maintaining the advantages of both solid and gel electrolytes. In this study, a curated dataset of 120 data points representing eight different polymers was used to predict ionic conductivity in imidazolium-based PILs as well as the emerging ionene substructures. For this purpose, four ML models: CatBoost, Random Forest, XGBoost, and LightGBM were employed by incorporating chemical structure and temperature as the models’ inputs. The best-performing model was further employed to estimate the conductivity of novel ionenes, offering insights into the potential of advanced polymer architectures for next-generation LIB electrolytes. This approach provides a cost-effective and intelligent pathway to accelerate the design of high-performance electrolyte materials. Full article

With the popularization of social media, information related to public health events has seen explosive growth online, making it essential to accurately identify informative tweets with decision-making and management value for public health emergency response and risk monitoring. However, existing methods often suffer performance degradation during cross-event transfer due to differences in data distribution, and research specifically targeting public health events remains limited. To address this, we propose the Label Confusion Domain Adversarial Network (LCDAN), which innovatively integrates label confusion with domain adaptation to enhance the detection of informative tweets across different public health events. First, LCDAN employs an adversarial domain adaptation model to learn cross-domain feature representation. Second, it dynamically evaluates the importance of different source domain samples to the target domain through label confusion to optimize the migration effect. Experiments were conducted on datasets related to COVID-19, Ebola disease, and Middle East Respiratory Syndrome public health events. The results demonstrate that LCDAN significantly outperforms existing methods across all tasks. This research provides an effective tool for information detection during public health emergencies, with substantial theoretical and practical implications. Full article

Artificial neural networks (ANNs) adjust to the underlying behavior in the dataset using a training rule or optimizer. The most popular first-and second-order optimizers, Adam (AD) and Levenberg–Marquardt (LM), were compared with the aim of predicting extreme flash floods of a runoff-dominated hydrological system. A fully connected multilayer perceptron with a shallow structure was used to reduce complexity and limit overfitting. The inputs of the ANN were determined by rainfall–water level cross-correlation analysis. For each optimizer, the hyperparameters of the ANN were selected using a grid search and the cross-validation score on a novel criterion (PERS PEAK) mixing the persistency (PERS) and the quality of flood-peak restitution (PEAK). For an extreme and unseen event used as a test set, LM outperformed AD by 25% on all performance criteria. The peak water level of this event, 66% greater than that of the training set, was predicted by 92% after more training iterations were done by the LM optimizer. This shows that the ANN can predict beyond the ranges of the training set, given the right optimizer. Nevertheless, the LM training time was up to five times longer than that of AD during grid search. Full article

Single-cell RNA sequencing (scRNA-seq) has revolutionized molecular biology and genomics by enabling the profiling of individual cell types, providing insights into cellular heterogeneity. Deep learning methods have become popular in single cell analysis for tasks such as dimension reduction, cell clustering, and data imputation. In this work, we introduce DropDAE, a denoising autoencoder (DAE) model enhanced with contrastive learning, to specifically address the dropout events in scRNA-seq data, where certain genes show very low or even zero expression levels due to technical limitations. DropDAE uses the architecture of a denoising autoencoder to recover the underlying data patterns while leveraging contrastive learning to enhance group separation. Our extensive evaluations across multiple simulation settings based on synthetic data and a real-world dataset demonstrate that DropDAE not only reconstructs data effectively but also further improves clustering performance, outperforming existing methods in terms of accuracy and robustness. Full article

News recommendation systems must simultaneously address multiple challenges, including dynamic user interest modeling, nonlinear popularity patterns, and diversity recommendation in cold-start scenarios. We present a Popularity-Aware Dynamic Multi-Perspective Fusion Network (PAD-MPFN) that innovatively integrates three key components: adaptive subspace projection for multi-source interest fusion, logarithmic time-decay factors for popularity bias mitigation, and dynamic gating mechanisms for personalized recommendation weighting. The framework uniquely combines sequential behavior analysis, social graph propagation, and temporal popularity modeling through a unified architecture. Experimental results on the MIND dataset, an open-source version of MSN News, demonstrate that PAD-MPFN outperforms existing methods in terms of recommendation performance and cold-start scenarios while effectively alleviating information overload. This study offers a new solution for dynamic interest modeling and diverse recommendation. Full article

Cassava is the sixth most important food crop and is cultivated in more than 100 countries. The crop tolerates low soil fertility and drought, enabling it to play a role in climate adaptation strategies. Cassava generally requires careful preparation to remove toxic hydrogen cyanide (HCN) before its consumption, but HCN concentrations can vary considerably between varieties. Climate change and low inputs, particularly carbon and nutrients, affect agriculture in Pacific Island countries where cassava is commonly grown alongside traditional crops (e.g., taro). Despite increasing popularity in this region, there is limited experimental data about cassava crop management for different local varieties, their relative toxicity and nutritional value for human consumption, and their interaction with changing climate conditions. To help address this knowledge gap, three field experiments were conducted at the Koronivia Research Station of the Fiji Ministry of Agriculture. Two varieties of cassava with contrasting HCN content were planted at three different times coinciding with the start of the wet (September-October) or dry (April) seasons. A time series of measurements was conducted during the full 18-month or differing 6-month durations of each crop, based on destructive harvests and phenological observations. The former included determination of total biomass, HCN potential, carbon isotopes (δ¹³C), and elemental composition. Yield and nutritional value were significantly affected by variety and time of planting, and there were interactions between the two factors. Findings from this work will improve cassava management locally and will provide a valuable dataset for agronomic and biophysical model testing. Full article

Soccer’s global popularity as the world’s favorite sport is driven by many factors, with high player salaries being one of the key reasons behind its appeal. These salaries not only reflect on-field performance, but also capture a broader evaluation of player value. Despite the increasing use of performance data in sports analytics, a critical gap remains in establishing fair compensation models that comprehensively account for both quantifiable and intangible contributions. To address these challenges, this study adopts machine learning (ML) techniques that model player salaries based on a combination of performance metrics and contextual features. This research focuses on reducing bias and improving transparency in salary decisions through a systematic, data-driven approach. Utilizing a dataset spanning the 2016–2022 seasons, we apply both traditional and automated ML frameworks to uncover the most influential factors in salary determination. The results indicate a nearly 17% improvement in R² and about a 30% reduction in MAE after incorporating the newly constructed features and methods, demonstrating a significant enhancement in model performance. Gradient Boosting demonstrates superior effectiveness, revealing a group of significantly underestimated and overestimated players, and showcasing the model’s proficiency in detecting valuation discrepancies. Full article

Image binarization is an important process in many computer-vision applications. This transforms the color space of the original image into black and white. Global thresholding is a quick and reliable way to achieve binarization, but it is inherently limited by image noise and uneven lighting. This paper introduces a global thresholding method that uses the results of classical global thresholding algorithms and other global image features to train a regression model via machine learning. We prove through nested cross-validation that the model can predict the best possible global threshold with an average F-measure of 90.86% and a confidence of 0.79%. We apply our approach to a popular computer vision problem, document image binarization, and compare popular metrics with the best possible values achievable through global thresholding and with the values obtained through the algorithms we used to train our model. Our results show a significant improvement over these classical global thresholding algorithms, achieving near-perfect scores on all the computed metrics. We also compared our results with state-of-the-art binarization algorithms and outperformed them on certain datasets. The global threshold obtained through our method closely approximates the ideal global threshold and could be used in a mixed local-global approach for better results. Full article

The emergence of the Internet of Vehicles (IoV) has revolutionized intelligent transportation and communication systems. However, IoV presents many complex and ever-changing security challenges and thus requires robust cybersecurity protocols. This paper comprehensively describes and evaluates ensemble learning approaches for multi-class intrusion detection systems in the IoV environment. The study evaluates several approaches, such as stacking, voting, boosting, and bagging. A comprehensive review of the literature spanning 2020 to 2025 reveals important trends and topics that require further investigation and the relative merits of different ensemble approaches. The NSL-KDD, CICIDS2017, and UNSW-NB15 datasets are widely used to evaluate the performance of Ensemble Learning-Based Intrusion Detection Systems (ELIDS). ELIDS evaluation is usually carried out using some popular performance metrics, including Precision, Accuracy, Recall, F1-score, and Area Under Receiver Operating Characteristic Curve (AUC-ROC), which were used to evaluate and measure the effectiveness of different ensemble learning methods. Given the increasing complexity and frequency of cyber threats in IoV environments, ensemble learning methods such as bagging, boosting, and stacking enhance adaptability and robustness. These methods aggregate multiple learners to improve detection rates, reduce false positives, and ensure more resilient intrusion detection models that can evolve alongside emerging attack patterns. Full article

Face-to-face interaction is one of the most natural forms of human communication. Unsurprisingly, Video Conferencing (VC) Applications have experienced a significant rise in demand over the past decade. With the widespread availability of cellular devices equipped with high-resolution cameras, Instant Messaging Video Call Applications (IMVCAs) now constitute a substantial portion of VC communications. Given the multitude of IMVCA options, maintaining a high Quality of Experience (QoE) is critical. While content providers can measure QoE directly through end-to-end connections, Internet Service Providers (ISPs) must infer QoE indirectly from network traffic—a non-trivial task, especially when most traffic is encrypted. In this paper, we analyze a large dataset collected from WhatsApp IMVCA, comprising over 25,000 s of VC sessions. We apply four Machine Learning (ML) algorithms and a Large Multimodal Model (LMM)-based agent, achieving mean errors of 4.61%, 5.36%, and 13.24% for three popular QoE metrics: BRISQUE, PIQE, and FPS, respectively. Full article

Laser-induced breakdown spectroscopy (LIBS) has played a critical role in Mars exploration missions, substantially contributing to the geochemical analysis of Martian surface substances. However, the complex nonlinearity of LIBS processes can considerably limit the quantification accuracy of conventional LIBS chemometric methods. Hence chemometrics based on artificial neural network (ANN) algorithms have become increasingly popular in LIBS analysis due to their extraordinary ability in nonlinear feature modeling. The hidden layer activation functions are key to ANN model performance, yet common activation functions usually suffer from problems such as gradient vanishing (e.g., Sigmoid and Tanh) and dying neurons (e.g., ReLU). In this study, we propose a novel LIBS quantification method, named the Bayesian optimization-based tunable Softplus backpropagation neural network (BOTS-BPNN). Based on a dataset comprising 1800 LIBS spectra collected by a laboratory duplicate of the MarSCoDe instrument onboard the Zhurong Mars rover, we have revealed that a BPNN model adopting a tunable Softplus activation function can achieve higher prediction accuracy than BPNN models adopting other common activation functions if the tunable Softplus parameter β is properly selected. Moreover, the way to find the proper β value has also been investigated. We demonstrate that the Bayesian optimization method surpasses the traditional grid search method regarding both performance and efficiency. The BOTS-BPNN model also shows superior performance over other common machine learning models like random forest (RF). This work indicates the potential of BOTS-BPNN as an effective chemometric method for analyzing Mars in situ LIBS data and sheds light on the use of chemometrics for data analysis in future planetary explorations. Full article