Search Results (527)

Detecting previously unseen anomalies in sensor data is a challenging problem for artificial intelligence when sensor-specific and deployment-specific characteristics of the time series need to be learned from a short calibration period. From the application point of view, this challenge becomes increasingly important because many applications are gravitating towards utilising low-cost sensors for Internet of Things deployments. While these sensors offer cost-effectiveness and customisation, their data quality does not match that of their high-end counterparts. To improve sensor data quality while addressing the challenges of anomaly detection in Internet of Things applications, we present an anomaly detection framework that learns a normality model of sensor data. The framework models the typical behaviour of individual sensors, which is crucial for the reliable detection of sensor data anomalies, especially when dealing with sensors observing significantly different signal characteristics. Our framework learns sensor-specific normality models from a small set of anomaly-free training data while employing an unsupervised feature engineering approach to select statistically significant features. The selected features are subsequently used to train a Local Outlier Factor anomaly detection model, which adaptively determines the boundary separating normal data from anomalies. The proposed anomaly detection framework is evaluated on three real-world public environmental monitoring datasets with heterogeneous sensor readings. The sensor-specific normality models are learned from extremely short calibration periods (as short as the first 3 days or 10% of the total recorded data) and outperform four other state-of-the-art anomaly detection approaches with respect to F1-score (between 5.4% and 9.3% better) and Matthews correlation coefficient (between 4.0% and 7.6% better). Full article

Chronic kidney disease (CKD) is a heterogeneous condition with various etiologies, including type 2 diabetes mellitus (T2D), hypertension, and autoimmune disorders. Both diabetic CKD (CKD_T2D) and non-diabetic CKD (CKD_nonT2D) share overlapping clinical features, but understanding the molecular mechanisms underlying each subtype and distinguishing diabetic from non-diabetic forms remain poorly defined. To identify differentially expressed genes (DEGs) and enriched biological pathways between CKD_T2D and CKD_nonT2D cohorts, including autoimmune (CKD_nonT2D_AI) and hypertensive (CKD_nonT2D_HT) subtypes, through integrative transcriptomic analysis. Publicly available gene expression datasets from human glomerular and tubulointerstitial kidney tissues were curated and analyzed from GEO and ArrayExpress. Differential expression analysis and Gene Set Enrichment Analysis (GSEA) were conducted to assess cohort-specific molecular signatures. A considerable overlap in DEGs was observed between CKD_T2D and CKD_nonT2D, with CKD_T2D exhibiting more extensive gene expression changes. Hypertensive-CKD shared greater transcriptomic similarity with CKD_T2D than autoimmune-CKD. Key DEGs involved in fibrosis, inflammation, and complement activation—including Tgfb1, Timp1, Cxcl6, and C1qa/B—were differentially regulated in diabetic samples, where GSEA revealed immune pathway enrichment in glomeruli and metabolic pathway enrichment in tubulointerstitium. The transcriptomic landscape of CKD_T2D reveals stronger immune and metabolic dysregulation compared to non-diabetic CKD. These findings suggest divergent pathological mechanisms and support the need for tailored therapeutic approaches. Full article

Glioblastoma (GBM) is a highly aggressive and heterogeneous brain tumor. Glioma stem-like cells (GSCs) play a central role in tumor progression, therapeutic resistance, and recurrence. Although immune cells are known to shape the GBM microenvironment, the impact of antigen-presenting-cell (APC) signature genes on tumor-intrinsic phenotypes remains underexplored. We analyzed both bulk- and single-cell RNA sequencing datasets of GBM to investigate the association between APC gene expression and tumor-cell states, including stemness and metabolic reprogramming. Signature scores were computed using curated gene sets related to APC activity, KEGG metabolic pathways, and cancer hallmark pathways. Protein–protein interaction (PPI) networks were constructed to examine the links between immune regulators and metabolic programs. The high expression of APC-related genes, such as HLA-DRA, CD74, CD80, CD86, and CIITA, was associated with lower stemness signatures and enhanced inflammatory signaling. These APC-high states (mean difference = –0.43, adjusted p < 0.001) also showed a shift in metabolic activity, with decreased oxidative phosphorylation and increased lipid and steroid metabolism. This pattern suggests coordinated changes in immune activity and metabolic status. Furthermore, TNF-α and other inflammatory markers were more highly expressed in the less stem-like tumor cells, indicating a possible role of inflammation in promoting differentiation. Our findings revealed that elevated APC gene signatures are associated with more differentiated and metabolically specialized GBM cell states. These transcriptional features may also reflect greater immunogenicity and inflammation sensitivity. The APC metabolic signature may serve as a useful biomarker to identify GBM subpopulations with reduced stemness and increased immune engagement, offering potential therapeutic implications. Full article

The integration of unmanned aerial vehicles (UAVs) into next-generation wireless networks greatly enhances the flexibility and efficiency of communication and distributed computation for ground mobile devices. Federated learning (FL) provides a privacy-preserving paradigm for device collaboration but remains highly vulnerable to poisoning attacks and is further challenged by the resource constraints and heterogeneous data common to UAV-assisted systems. Existing robust aggregation and anomaly detection methods often degrade in efficiency and reliability under these realistic adversarial and non-IID settings. To bridge these gaps, we propose FedULite, a lightweight and robust federated learning framework specifically designed for UAV-assisted environments. FedULite features unsupervised local representation learning optimized for unlabeled, non-IID data. Moreover, FedULite leverages a robust, adaptive server-side aggregation strategy that uses cosine similarity-based update filtering and dimension-wise adaptive learning rates to neutralize sophisticated data and model poisoning attacks. Extensive experiments across diverse datasets and adversarial scenarios demonstrate that FedULite reduces the attack success rate (ASR) from over 90% in undefended scenarios to below 5%, while maintaining the main task accuracy loss within 2%. Moreover, it introduces negligible computational overhead compared to standard FedAvg, with approximately 7% additional training time. Full article

Multiple cluster validity indices (CVIs) have been introduced for diverse applications. In practice, clusters exhibit varying shapes, sizes, densities, and closely spaced centers, which are typically unknown beforehand. It is desirable to develop a versatile CVI that performs well in general settings rather than being tailored to specific ones. Drawing inspiration from distance based on local density, where it is observed that cluster centers feature higher densities than their neighbors and are relatively distant from higher-density points, this paper introduces a novel CVI. This CVI employs a modified distance, adjusted for local density, to measure cluster compactness, replacing the traditional Euclidean distance with the minimum distance to a higher-density point. This adjustment accounts for cluster shapes and densities. The experimental results highlight the proposed index’s dual capability: it not only outperforms conventional methods by a remarkable margin of 32 percentage points in controlled synthetic environments but also maintains a 23+ percentage-point accuracy lead in real-world data regimes characterized by noise and heterogeneity. This consistency validates its generalizability across data modalities. Full article

The accurate estimation and prediction of internal states in lithium-ion (Li-Ion) batteries, such as State of Charge (SoC) and Remaining Useful Life (RUL), are vital for optimizing battery performance, safety, and longevity in electric vehicles and other applications. This paper presents a unified, modular, and extensible machine learning (ML) framework designed to address the heterogeneity and complexity of battery state prediction tasks. The proposed framework supports flexible configurations across multiple dimensions, including feature engineering, model selection, and training/testing strategies. It integrates standardized data processing pipelines with a diverse set of ML models, such as a long short-term memory neural network (LSTM), a convolutional neural network (CNN), a feedforward neural network (FFNN), automated machine learning (AutoML), and classical regressors, while accommodating heterogeneous datasets. The framework’s applicability is demonstrated through five distinct use cases involving SoC estimation and RUL prediction using real-world and benchmark datasets. Experimental results highlight the framework’s adaptability, methodological transparency, and robust predictive performance across various battery chemistries, usage profiles, and degradation conditions. This work contributes to a standardized approach that facilitates the reproducibility, comparability, and practical deployment of ML-based battery analytics. Full article

Background/Objectives: The accurate identification of insect bites from images of skin is daunting due to the fine gradations among diverse bite types, variability in human skin response, and inconsistencies in image quality. Methods: For this work, we introduce DeepBiteNet, a new ensemble-based deep learning model designed to perform robust multiclass classification of insect bites from RGB images. Our model aggregates three semantically diverse convolutional neural networks—DenseNet121, EfficientNet-B0, and MobileNetV3-Small—using a stacked meta-classifier designed to aggregate their predicted outcomes into an integrated, discriminatively strong output. Our technique balances heterogeneous feature representation with suppression of individual model biases. Our model was trained and evaluated on a hand-collected set of 1932 labeled images representing eight classes, consisting of common bites such as mosquito, flea, and tick bites, and unaffected skin. Our domain-specific augmentation pipeline imputed practical variability in lighting, occlusion, and skin tone, thereby boosting generalizability. Results: Our model, DeepBiteNet, achieved a training accuracy of 89.7%, validation accuracy of 85.1%, and test accuracy of 84.6%, and surpassed fifteen benchmark CNN architectures on all key indicators, viz., precision (0.880), recall (0.870), and F1-score (0.875). Our model, optimized for mobile deployment with quantization and TensorFlow Lite, enables rapid on-client computation and eliminates reliance on cloud-based processing. Conclusions: Our work shows how ensemble learning, when carefully designed and combined with realistic data augmentation, can boost the reliability and usability of automatic insect bite diagnosis. Our model, DeepBiteNet, forms a promising foundation for future integration with mobile health (mHealth) solutions and may complement early diagnosis and triage in dermatologically underserved regions. Full article

Skin cancer is one of the most prevalent forms of cancer worldwide, and early and accurate diagnosis critically impacts patient outcomes. Given the sensitive nature of medical data and its fragmented distribution across institutions (data silos), privacy-preserving collaborative learning is essential to enable knowledge-sharing without compromising patient confidentiality. While federated learning (FL) offers a promising solution, existing methods struggle with heterogeneous and missing modalities across institutions, which reduce the diagnostic accuracy. To address these challenges, we propose an effective and flexible Personalized Multimodal Federated Learning framework (PMM-FL), which enables efficient cross-client knowledge transfer while maintaining personalized performance under heterogeneous and incomplete modality conditions. Our study contains three key contributions: (1) A hierarchical aggregation strategy that decouples multi-module aggregation from local deployment via global modular-separated aggregation and local client fine-tuning. Unlike conventional FL (which synchronizes all parameters in each round), our method adopts a frequency-adaptive synchronization mechanism, updating parameters based on their stability and functional roles. (2) A multimodal fusion approach based on multitask learning, integrating learnable modality imputation and attention-based feature fusion to handle missing modalities. (3) A custom dataset combining multi-year International Skin Imaging Collaboration(ISIC) challenge data (2018–2024) to ensure comprehensive coverage of diverse skin cancer types. We evaluate PMM-FL through diverse experiment settings, demonstrating its effectiveness in heterogeneous and incomplete modality federated learning settings, achieving 92.32% diagnostic accuracy with only a 2% drop in accuracy under 30% modality missingness, with a 32.9% communication overhead decline compared with baseline FL methods. Full article

Gleason score (GS) is one of the best predictors of prostate cancer (PCa) aggressiveness; however, its biological features need to be elucidated. This study aimed to explore the biological characteristics of localized/locally advanced PCa stratified using in silico GS analysis. Biological features were analyzed using gene set variation analysis and the xCell algorithm with mRNA expression in two independent public databases: The Cancer Genome Atlas (TCGA) (n = 493; radical prostatectomy cohort) and GSE116918 (n = 248; radiation therapy cohort). GS levels were positively correlated with the activity levels of cell proliferation-related gene sets, including E2F targets, the G2M checkpoint, the mitotic spindle, and MYC targets v1 and v2 in both cohorts. Furthermore, GS levels were positively associated with the activity levels of immune-related gene sets and infiltrating fractions of immune cells, including CD4+ memory T cells, dendritic cells, M1 macrophages, and Th2 cells, in both cohorts. Notably, GS levels were positively associated with the score levels of homologous recombination defects, intratumor heterogeneity, fraction genome alteration, neoantigens, and mutation rates in the TCGA cohort. In conclusion, PCa with high GS levels was associated with cancer cell proliferation, immune cell infiltration, and high mutation rates, which may reflect worse clinical outcomes. Full article

In rice detection tasks, accurate identification of leaf streaks, pest and disease distribution, and spikelet hierarchies relies on high-quality images to distinguish between texture and hierarchy. However, existing images often suffer from texture blurring and contour shifting due to equipment and environment limitations, which affects the detection performance. In view of the fact that pests and diseases affect the whole situation and tiny details are mostly localized, we propose a rice image reconstruction method based on an adaptive two-branch heterogeneous structure. The method consists of a low-frequency branch (LFB) that recovers global features using orientation-aware extended receptive fields to capture streaky global features, such as pests and diseases, and a high-frequency branch (HFB) that enhances detail edges through an adaptive enhancement mechanism to boost the clarity of local detail regions. By introducing the dynamic weight fusion mechanism (CSDW) and lightweight gating network (LFFN), the problem of the unbalanced fusion of frequency information for rice images in traditional methods is solved. Experiments on the 4× downsampled rice test set demonstrate that the proposed method achieves a 62% reduction in parameters compared to EDSR, 41% lower computational cost (30 G) than MambaIR-light, and an average PSNR improvement of 0.68% over other methods in the study while balancing memory usage (227 M) and inference speed. In downstream task validation, rice panicle maturity detection achieves a 61.5% increase in mAP50 (0.480 → 0.775) compared to interpolation methods, and leaf pest detection shows a 2.7% improvement in average mAP50 (0.949 → 0.975). This research provides an effective solution for lightweight rice image enhancement, with its dual-branch collaborative mechanism and dynamic fusion strategy establishing a new paradigm in agricultural rice image processing. Full article

The need to improve medical diagnosis is of utmost importance in medical research, consisting of the optimization of accurate classification models able to assist clinical decisions. To minimize the errors that can be caused by using a single classifier, the voting ensemble technique can be used, combining the classification results of different classifiers to improve the final classification performance. This paper aims to compare the existing voting ensemble techniques with a new game-theory-derived approach based on Shapley values. We extended this method, originally developed for binary tasks, to the multi-class setting in order to capture complementary information provided by different classifiers. In heterogeneous clinical scenarios such as thyroid nodule diagnosis, where distinct models may be better suited to identify specific subtypes (e.g., benign, malignant, or inflammatory lesions), ensemble strategies capable of leveraging these strengths are particularly valuable. The motivating application focuses on the classification of thyroid cancer nodules whose cytopathological clinical diagnosis is typically characterized by a high number of false positive cases that may result in unnecessary thyroidectomy. We apply and compare the performance of seven individual classifiers, along with four ensemble voting techniques (including Shapley values), in a real-world study focused on classifying thyroid cancer nodules using proteomic features obtained through mass spectrometry. Our results indicate a slight improvement in the classification accuracy for ensemble systems compared to the performance of single classifiers. Although the Shapley value-based voting method remains comparable to the other voting methods, we envision this new ensemble approach could be effective in improving the performance of single classifiers in further applications, especially when complementary algorithms are considered in the ensemble. The application of these techniques can lead to the development of new tools to assist clinicians in diagnosing thyroid cancer using proteomic features derived from mass spectrometry. Full article

Federated learning (FL) has emerged as a prominent distributed machine learning paradigm that facilitates collaborative model training across multiple clients while ensuring data privacy. Despite its growing adoption in practical applications, performance degradation caused by data heterogeneity—commonly referred to as the non-independent and identically distributed (non-IID) nature of client data—remains a fundamental challenge. To mitigate this issue, a heterogeneity-aware and robust FL framework is proposed to enhance model generalization and stability under non-IID conditions. The proposed approach introduces two key innovations. First, a heterogeneity quantification mechanism is designed based on statistical feature distributions, enabling the effective measurement of inter-client data discrepancies. This metric is further employed to guide the model aggregation process through a heterogeneity-aware weighted strategy. Second, a multi-loss optimization scheme is formulated, integrating classification loss, heterogeneity loss, feature center alignment, and L2 regularization for improved robustness against distributional shifts during local training. Comprehensive experiments are conducted on four benchmark datasets, including CIFAR-10, SVHN, MNIST, and NotMNIST under Dirichlet-based heterogeneity settings (alpha = 0.1 and alpha = 0.5). The results demonstrate that the proposed method consistently outperforms baseline approaches such as FedAvg, FedProx, FedSAM, and FedMOON. Notably, an accuracy improvement of approximately 4.19% over FedSAM is observed on CIFAR-10 (alpha = 0.5), and a 1.82% gain over FedMOON on SVHN (alpha = 0.1), along with stable enhancements on MNIST and NotMNIST. Furthermore, ablation studies confirm the contribution and necessity of each component in addressing data heterogeneity. Full article

Remote sensing visual grounding, a pivotal technology bridging natural language and high-resolution remote sensing images, holds significant application value in disaster monitoring, urban planning, and related fields. However, it faces critical challenges due to the inherent scale heterogeneity, semantic complexity, and annotation scarcity of remote sensing data. This paper first reviews the development history of remote sensing visual grounding, providing an overview of the basic background knowledge, including fundamental concepts, datasets, and evaluation metrics. Then, it categorizes methods by whether they employ large language models as a pedestal, and provides in-depth analyses of the innovations and limitations of Transformer-based and multimodal large language model-based methods. Furthermore, focusing on remote sensing image characteristics, it discusses cutting-edge techniques such as cross-modal feature fusion, language-guided visual optimization, multi-scale, and hierarchical feature processing, open-set expansion and efficient fine-tuning. Finally, it outlines current bottlenecks and proposes valuable directions for future research. As the first comprehensive review dedicated to remote sensing visual grounding, this work is a reference resource for researchers to grasp domain-specific concepts and track the latest developments. Full article

Acinetobacter baumannii is listed by the World Health Organization as an emerging bacterial priority pathogen, the prevalence and multidrug resistance of which have been increasing. This functional genomics study aimed to understand the drug-resistance mechanisms of an extensively drug-resistant (XDR) A. baumannii strain (IRMCBCU95U) isolated from a transtracheal aspirate sample from a female patient with end-stage renal disease in Saudi Arabia. The whole genome of IRMCBCU95U (4.3 Mbp) was sequenced using Oxford Nanopore long-read sequencing to identify and compare the antibiotic-resistance profile and genomic features of A. baumannii IRMCBCU95U. The antibiogram of A. baumannii IRMCBCU95U revealed resistance to multiple antibiotics, including cefepime, ceftazidime, ciprofloxacin, imipenem, meropenem and piperacillin/tazobactam. A comparative genomic analysis between IRMCBCU95U and A. baumannii K09-14 and ATCC 19606 identified significant genetic heterogeneity and mosaicism among the strains. This analysis also demonstrated the hybrid nature of the genome of IRMCBCU95U and indicates that horizontal gene transfer may have occurred between these strains. The IRMCBCU95U genome has a diverse range of genes associated with antimicrobial resistance and mobile genetic elements (ISAba1 and IS26) associated with the spread of multidrug resistance. The presence of virulence-associated genes that are linked to iron acquisition, motility and transcriptional regulation confirmed that IRMCBCU95U is a priority human pathogen. The plasmid fragment IncFIB(pNDM-Mar) observed in the strain is homologous to the plasmid in Klebsiella pneumoniae (439 bp; similarity: 99.09%), which supports its antimicrobial resistance. From these observations, it can be concluded that the clinical A. baumannii IRMCBCU95U isolate is an emerging extensively drug-resistant human pathogen with a novel combination of resistance genes and a plasmid fragment. The complex resistome of IRMCBCU95U highlights the urgent need for genomic surveillance in hospital settings in Saudi Arabia to fight against the spread of extensively drug-resistant A. baumannii. Full article

The discovery of proteomic biomarkers in cancer research can be effectively performed in situ by exploiting Matrix-Assisted Laser Desorption Ionization (MALDI) Mass Spectrometry Imaging (MSI). However, due to experimental limitations, the spectra extracted by MALDI-MSI can be noisy, so pre-processing steps are generally needed to reduce the instrumental and analytical variability. Thus far, the importance and the effect of standard pre-processing methods, as well as their combinations and parameter settings, have not been extensively investigated in proteomics applications. In this work, we present a systematic study of 15 combinations of pre-processing steps—including baseline, smoothing, normalization, and peak alignment—for a real-data classification task on MALDI-MSI data measured from fine-needle aspirates biopsies of thyroid nodules. The influence of each combination was assessed by analyzing the feature extraction, pixel-by-pixel classification probabilities, and LASSO classification performance. Our results highlight the necessity of fine-tuning a pre-processing pipeline, especially for the reliable transfer of molecular diagnostic signatures in clinical practice. We outline some recommendations on the selection of pre-processing steps, together with filter levels and alignment methods, according to the mass-to-charge range and heterogeneity of data. Full article