Search Results (27)

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing semantic segmentation methods still suffer from inadequate target recognition capabilities and multi-scale representation issues. This paper proposes a neural network model, LMVMamba (LoRA Multi-scale Vision Mamba), for semantic segmentation of remote sensing images. This model integrates the advantages of convolutional neural networks (CNNs), Transformers, and state-space models (Mamba) with a multi-scale feature fusion strategy. It simultaneously captures global contextual information and fine-grained local features. Specifically, in the encoder stage, the ResT Transformer serves as the backbone network, employing a LoRA fine-tuning strategy to effectively enhance model accuracy by training only the introduced low-rank matrix pairs. The extracted features are then passed to the decoder, where a U-shaped Mamba decoder is designed. In this stage, a Multi-Scale Post-processing Block (MPB) is introduced, consisting of depthwise separable convolutions and residual concatenation. This block effectively extracts multi-scale features and enhances local detail extraction after the VSS block. Additionally, a Local Enhancement and Fusion Attention Module (LAS) is added at the end of each decoder block. LAS integrates the SimAM attention mechanism, further enhancing the model’s multi-scale feature fusion capability and local detail segmentation capability. Through extensive comparative experiments, it was found that LMVMamba achieves superior performance on the OpenEarthMap dataset (mIoU 52.3%, OA 69.8%, mF1: 68.0%) and LoveDA (mIoU 67.9%, OA 80.3%, mF1: 80.5%) datasets. Ablation experiments validated the effectiveness of each module. The final results indicate that this model is highly suitable for high-precision land-cover classification tasks in remote sensing imagery. LMVMamba provides an effective solution for precise semantic segmentation of high-resolution remote sensing imagery. Full article

Objectives: The objective of this study was to investigate the prognostic value of systemic inflammatory markers (SIMs)—namely, the neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR)—on survival outcomes and treatment responses in patients with metastatic castration-resistant prostate cancer (mCRPC) receiving abiraterone (ABI) or enzalutamide (ENZA) therapy. Methods: In this two-center retrospective observational study, researchers analyzed clinical data from 106 patients diagnosed with mCRPC. The cut-offs for NLR and PLR were determined to be 2.83 and 156, respectively, and their effects on progression-free survival (PFS) and overall survival (OS) were evaluated using Kaplan–Meier and Cox regression analyses. Changes in SIMs before and after ABI/ENZA treatment were assessed using the Wilcoxon signed-rank test. Results: Lower NLR (≤2.83) and PLR (≤156) were significantly associated with longer PFS and OS; however, in multivariate analysis, only high PLR emerged as an independent adverse prognostic factor for OS (HR: 2.01; p = 0.026). Meanwhile, treatment response was an independent predictor of PFS, and no significant changes were observed in the mean platelet volume (MPV), platelet distribution width (PDW), or platelet–large cell ratio (P-LCR) after treatment. Conclusions: SIMs, such as NLR and especially PLR, may serve as practical and accessible tools for predicting survival in mCRPC patients; however, further prospective studies are warranted. Full article

The widespread integration of third-party components (TPCs) in Internet of Things (IoT) firmware significantly increases the risk of software vulnerabilities, especially in resource-constrained devices deployed in sensitive environments. Binary Code Similarity Detection (BCSD) techniques, particularly those based on deep neural networks, have emerged as powerful tools for identifying vulnerable functions without access to source code. However, individual models, such as Graph Neural Networks (GNNs), Convolutional Neural Networks (CNNs), and Transformer-based methods, often exhibit limitations due to their differing focus on structural, spatial, or semantic features. To address this, we propose VoteSim, a novel ensemble framework that integrates multiple BCSD models using an inverse average rank voting mechanism. VoteSim combines the strengths of individual models while reducing the impact of model-specific false positives, leading to more stable and accurate vulnerability detection. We evaluate VoteSim on a large-scale real-world IoT firmware dataset comprising over 800,000 binary functions and 10 high-risk CVEs. Experimental results show that VoteSim consistently outperforms state-of-the-art BCSD models in both Recall@10 and Mean Reciprocal Rank (MRR), achieving improvements of up to 14.7% in recall. Our findings highlight the importance of model diversity and rank-aware aggregation for robust binary-level vulnerability detection in heterogeneous IoT firmware. Full article

With the growing demand for multilingual financial information, cross-lingual financial sentiment recognition faces significant challenges, including semantic misalignment, ambiguous sentiment expression, and insufficient transferability. To address these issues, a unified multilingual recognition framework is proposed, integrating semantic contrastive learning with a language-adaptive modulation mechanism. This approach is built upon the XLM-R multilingual model and employs a semantic contrastive module to enhance cross-lingual semantic consistency. In addition, a language modulation module based on low-rank parameter injection is introduced to improve the model’s sensitivity to fine-grained emotional features in low-resource languages such as Chinese and French. Experiments were conducted on a constructed trilingual financial sentiment dataset encompassing English, Chinese, and French. The results demonstrate that the proposed model significantly outperforms existing methods in cross-lingual sentiment recognition tasks. Specifically, in the English-to-French transfer setting, the model achieved 73.6% in accuracy, 69.8% in F1-Macro, 72.4% in F1-Weighted, and a cross-lingual generalization score of 0.654. Further improvements were observed under multilingual joint training, reaching 77.3%, 73.6%, 76.1%, and 0.696, respectively. In overall comparisons, the proposed model attained the highest performance across cross-lingual scenarios, with 75.8% in accuracy, 72.3% in F1-Macro, and 74.7% in F1-Weighted, surpassing strong baselines such as XLM-R+SimCSE and LaBSE. These results highlight the model’s superior capability in semantic alignment and generalization across languages. The proposed framework demonstrates strong applicability and promising potential in multilingual financial sentiment analysis, public opinion monitoring, and multilingual risk modeling. Full article

Workflow scheduling in cloud computing is attracting increasing attention. Cloud computing can assign tasks to available virtual machine resources in cloud data centers according to scheduling strategies, providing a powerful computing platform for the execution of workflow tasks. However, developing effective workflow scheduling algorithms to find optimal or near-optimal task-to-VM allocation solutions that meet users’ specific QoS requirements still remains an open area of research. In this paper, we propose a hybrid QoS-aware workflow scheduling algorithm named HLWOA to address the problem of simultaneously minimizing the completion time and execution cost of workflow scheduling in cloud computing. First, the workflow scheduling problem in cloud computing is modeled as a multi-objective optimization problem. Then, based on the heterogeneous earliest finish time (HEFT) heuristic optimization algorithm, tasks are reverse topologically sorted and assigned to virtual machines with the earliest finish time to construct an initial workflow task scheduling sequence. Furthermore, an improved Whale Optimization Algorithm (WOA) based on Lévy flight is proposed. The output solution of HEFT is used as one of the initial population solutions in WOA to accelerate the convergence speed of the algorithm. Subsequently, a Lévy flight search strategy is introduced in the iterative optimization phase to avoid the algorithm falling into local optimal solutions. The proposed HLWOA is evaluated on the WorkflowSim platform using real-world scientific workflows (Cybershake and Montage) with different task scales (100 and 1000). Experimental results demonstrate that HLWOA outperforms HEFT, HEPGA, and standard WOA in both makespan and cost, with normalized fitness values consistently ranking first. Full article

Alongside the general growth in gaming and esports, competitive simulated (sim) racing has specifically surged in popularity in recent years, leading to an increased demand for understanding performance. In recent work, braking-related metrics were identified among the key indicators of successful sim racing performance. While load cell sensors currently serve as the industry standard for brake hardware, sensors like the Hall sensor may provide another viable option. No study to date has compared the performance of these braking sensors. The aim of this study was to investigate whether sim racing performance differed when racing using a load cell or Hall brake sensor. Twenty (N = 20) experienced sim racers raced with both the load cell and Hall brake sensors (with load cell behaviour mimicked on the Hall sensor) in a repeated measures design. Paired samples t-tests, Wilcoxon-signed rank tests, and chi-square goodness-of-fit tests were used to test for differences in lap time, driving behaviour metrics, and subjective responses between the two sensors. Results showed that participants achieved faster lap times using the load cell brake sensor (average lap time (p = 0.071); fastest lap time (p = 0.052)) and displayed braking behaviour more aligned with that of a “faster racer”. The differences observed may be potentially attributed to differences in in-game response curves between two brake sensors, which specifically may impact both the initial, and trail braking, phases. Full article

Unsupervised sentence embedding, vital for numerous NLP tasks, struggles with the inherent asymmetry of semantic relationships within contrastive learning (CL). This paper proposes Label Smoothing-based Ranking Negative Sampling (LS-RNS), a novel framework that directly tackles the semantic asymmetry between anchor and negative samples in CL. LS-RNS utilizes a Large Language Model (LLM) to assess fine-grained asymmetric similarity scores between sentences, constructing a ranking-aware negative sampling strategy combined with adaptive label smoothing. This design encourages the model to learn more effectively from informative negatives that are semantically closer to the anchor, leading to asymmetry-aware sentence embeddings. Experiments on standard Semantic Textual Similarity (STS) benchmarks (STS12–STS16, STS-B, SICK-R) show that LS-RNS achieves state-of-the-art performance. We adopt Spearman’s rank correlation coefficient as the primary evaluation metric for semantic similarity tasks, and we use classification accuracy for downstream and transfer tasks. LS-RNS achieves 79.87 on STS tasks with BERT-base (vs. 76.25 for SimCSE, +3.62) and 80.41 with RoBERTa-base (vs. 79.18 for DiffCSE). On transfer tasks, it attains 88.82 (BERT) and 87.68 (RoBERTa), consistently outperforming PromptBERT and SNCSE. On STL-10, LS-RNS improves SimCLR top-one accuracy from 79.50% to 80.52% with ResNet-18 and from 68.91% to 72.19% with VGG-16, even enabling a shallow ResNet-18 to surpass a deeper ResNet-34 baseline. These results confirm the modality-agnostic effectiveness of LS-RNS and its potential to redefine contrastive learning objectives by modeling semantic asymmetry, rather than relying solely on encoder depth or pre-training objectives. Full article

Urban forests, as an integral part of nature-based solutions (NBS), are significant contributors to improving urban air quality, delivering ecological service functions and environmental benefits to human health and well-being. Suitable urban forest management, including proper species selection, needs to be defined to efficiently reduce air pollutants in cities, with a focus on the removal ability of the main air pollutants (PM_2.5, PM₁₀, O₃, and NO₂), the ecological adaptability to O₃ and NO₂, and allergenic effects. This study ranked 73 urban greening tree species in northern Chinese cities based on their ability to maximize air quality and minimize disservices. This study proposed a novel Species-Specific Air Purification Index (S-API), which is suitable for air quality improvement for tree/shrub species. Urban managers are recommended to select species with an S-API > 1.47—that is, species that have a high removal capacity of PM_2.5, PM₁₀, O₃, and NO₂, are O₃- and NO₂-tolerant, and are non-allergenic (e.g., Castanea mollissima Blume, Ginkgo biloba L., Hibiscus syriacus L., Ilex chinensis Sims, Juniperus procumbens (Endl.) Iwata et Kusaka, Liriodendron chinense (Hemsl.) Sarg., Morus alba L., Styphnolobium japonicum (L.) Schott, Syringa oblata Lindl., and Ulmus pumila L.). The S-API of urban greening species thus represents a potentially useful metric for air pollutant risk assessment and for selecting appropriate species for urban greening in cities facing serious air pollution challenges. Full article

The use of medicinal herbs is highly developed in Haiti. However, there is a significant lack of knowledge in the literature on medicinal plants and their uses. The objective of this study was to determine the knowledge and practices of Haitian families for the prevention/treatment of COVID-19, influenza, and respiratory diseases, as well as the mode of preparation and administration of the plants. Individuals were interviewed using the TRAMIL questionnaire as the information holder. The data obtained were analyzed by calculating 5 indices (relative frequency of citation, use value, the family use value, informant consensus factor, and fidelity level). The study surveyed 120 Haitians and collected 75 plants from 43 botanical families. The botanical family most used for all these preventions and remedies is the Lamiaceae. The highest ranked species with a relative frequency of citation value > 0.3. Infusion, decoction, and in the form of punch are the methods used for the remedies. The study found that the use of herbal remedies is still prevalent in the study area, and many of the commonly used plants have been scientifically validated. However, some plants, such as Samyda rosea Sims, lack sufficient research and are recommended for further investigation. Full article

SimRank is a widely used metric for evaluating vertex similarity based on graph topology, with diverse applications such as large-scale graph mining and natural language processing. The objective of the single-source and top-k SimRank query problem is to retrieve the kvertices with the largest SimRank to the source vertex. However, existing algorithms suffer from inefficiency as they require computing SimRank for all vertices to retrieve the top-k results. To address this issue, we propose an algorithm named HitSimthat utilizes a branch and bound strategy for the single-source and top-k query. HitSim initially partitions vertices into distinct sets based on their shortest-meeting lengths to the source vertex. Subsequently, it computes an upper bound of SimRank for each set. If the upper bound of a set is no larger than the minimum value of the current top-k results, HitSim efficiently batch-prunes the unpromising vertices within the set. However, in scenarios where the graph becomes dense, certain sets with large upper bounds may contain numerous vertices with small SimRank, leading to redundant overhead when processing these vertices. To address this issue, we propose an optimized algorithm named HitSim-OPT that computes the upper bound of SimRank for each vertex instead of each set, resulting in a fine-grained and efficient pruning process. The experimental results conducted on six real-world datasets demonstrate the performance of our algorithms in efficiently addressing the single-source and top-k query problem. Full article

Diabetic kidney disease (DKD) is the leading cause of end-stage renal disease worldwide. This study’s goal was to identify the signaling drivers and pathways that modulate glomerular endothelial dysfunction in DKD via artificial intelligence-enabled literature-based discovery. Cross-domain text mining of 33+ million PubMed articles was performed with SemNet 2.0 to identify and rank multi-scalar and multi-factorial pathophysiological concepts related to DKD. A set of identified relevant genes and proteins that regulate different pathological events associated with DKD were analyzed and ranked using normalized mean HeteSim scores. High-ranking genes and proteins intersected three domains—DKD, the immune response, and glomerular endothelial cells. The top 10% of ranked concepts were mapped to the following biological functions: angiogenesis, apoptotic processes, cell adhesion, chemotaxis, growth factor signaling, vascular permeability, the nitric oxide response, oxidative stress, the cytokine response, macrophage signaling, NF$\mathsf{\kappa }$B factor activity, the TLR pathway, glucose metabolism, the inflammatory response, the ERK/MAPK signaling response, the JAK/STAT pathway, the T-cell-mediated response, the WNT/$\mathsf{\beta }$-catenin pathway, the renin–angiotensin system, and NADPH oxidase activity. High-ranking genes and proteins were used to generate a protein–protein interaction network. The study results prioritized interactions or molecules involved in dysregulated signaling in DKD, which can be further assessed through biochemical network models or experiments. Full article

Multiple studies have reported new or exacerbated persistent or resistant hypertension in patients previously infected with COVID-19. We used literature-based discovery to identify and prioritize multi-scalar explanatory biology that relates resistant hypertension to COVID-19. Cross-domain text mining of 33+ million PubMed articles within a comprehensive knowledge graph was performed using SemNet 2.0. Unsupervised rank aggregation determined which concepts were most relevant utilizing the normalized HeteSim score. A series of simulations identified concepts directly related to COVID-19 and resistant hypertension or connected via one of three renin–angiotensin–aldosterone system hub nodes (mineralocorticoid receptor, epithelial sodium channel, angiotensin I receptor). The top-ranking concepts relating COVID-19 to resistant hypertension included: cGMP-dependent protein kinase II, MAP3K1, haspin, ral guanine nucleotide exchange factor, N-(3-Oxododecanoyl)-L-homoserine lactone, aspartic endopeptidases, metabotropic glutamate receptors, choline-phosphate cytidylyltransferase, protein tyrosine phosphatase, tat genes, MAP3K10, uridine kinase, dicer enzyme, CMD1B, USP17L2, FLNA, exportin 5, somatotropin releasing hormone, beta-melanocyte stimulating hormone, pegylated leptin, beta-lipoprotein, corticotropin, growth hormone-releasing peptide 2, pro-opiomelanocortin, alpha-melanocyte stimulating hormone, prolactin, thyroid hormone, poly-beta-hydroxybutyrate depolymerase, CR 1392, BCR-ABL fusion gene, high density lipoprotein sphingomyelin, pregnancy-associated murine protein 1, recQ4 helicase, immunoglobulin heavy chain variable domain, aglycotransferrin, host cell factor C1, ATP6V0D1, imipramine demethylase, TRIM40, H3C2 gene, COL1A1+COL1A2 gene, QARS gene, VPS54, TPM2, MPST, EXOSC2, ribosomal protein S10, TAP-144, gonadotropins, human gonadotropin releasing hormone 1, beta-lipotropin, octreotide, salmon calcitonin, des-n-octanoyl ghrelin, liraglutide, gastrins. Concepts were mapped to six physiological themes: altered endocrine function, 23.1%; inflammation or cytokine storm, 21.3%; lipid metabolism and atherosclerosis, 17.6%; sympathetic input to blood pressure regulation, 16.7%; altered entry of COVID-19 virus, 14.8%; and unknown, 6.5%. Full article

Parkinson’s disease (PD) is a movement disorder caused by a dopamine deficit in the brain. Current therapies primarily focus on dopamine modulators or replacements, such as levodopa. Although dopamine replacement can help alleviate PD symptoms, therapies targeting the underlying neurodegenerative process are limited. The study objective was to use artificial intelligence to rank the most promising repurposed drug candidates for PD. Natural language processing (NLP) techniques were used to extract text relationships from 33+ million biomedical journal articles from PubMed and map relationships between genes, proteins, drugs, diseases, etc., into a knowledge graph. Cross-domain text mining, hub network analysis, and unsupervised learning rank aggregation were performed in SemNet 2.0 to predict the most relevant drug candidates to levodopa and PD using relevance-based HeteSim scores. The top predicted adjuvant PD therapies included ebastine, an antihistamine for perennial allergic rhinitis; levocetirizine, another antihistamine; vancomycin, a powerful antibiotic; captopril, an angiotensin-converting enzyme (ACE) inhibitor; and neramexane, an N-methyl-D-aspartate (NMDA) receptor agonist. Cross-domain text mining predicted that antihistamines exhibit the capacity to synergistically alleviate Parkinsonian symptoms when used with dopamine modulators like levodopa or levodopa–carbidopa. The relationship patterns among the identified adjuvant candidates suggest that the likely therapeutic mechanism(s) of action of antihistamines for combatting the multi-factorial PD pathology include counteracting oxidative stress, amending the balance of neurotransmitters, and decreasing the proliferation of inflammatory mediators. Finally, cross-domain text mining interestingly predicted a strong relationship between PD and liver disease. Full article

Channel neural decoding is very promising as it outperforms the traditional channel decoding algorithms. Unfortunately, it still faces the disadvantage of high computational complexity and storage complexity compared with the traditional decoding algorithms. In this paper, we propose that low rank decomposition techniques based on tensor train decomposition and tensor ring decomposition can be utilized in neural offset min-sum (NOMS) and neural scale min-sim (NSMS) decoding algorithms. The experiment results show that the proposed two algorithms achieve near state-of-the-art performance with low complexity. Full article

In modern biology and medicine, drug-drug similarity is a major task with various applications in pharmaceutical drug development. Various direct and indirect sources of evidence obtained from drug-centric data such as side effects, drug interactions, biological targets, and chemical structures are used in the current methods to measure the level of drug-drug similarity. This paper proposes a computational method to measure drug-drug similarity using a novel source of evidence that is obtained from patient-centric data. More specifically, patients’ narration of their thoughts, opinions, and experience with drugs in social media are explored as a potential source to compute drug-drug similarity. Online healthcare communities were used to extract a dataset of patients’ reviews on anti-epileptic drugs. The collected dataset is preprocessed through Natural Language Processing (NLP) techniques and four text similarity methods are applied to measure the similarities among them. The obtained similarities are then used to generate drug-drug similarity-based ranking matrices which are analyzed through Pearson correlation, to answer questions related to the overall drug-drug similarity and the accuracy of the four similarity measures. To evaluate the obtained drug-drug similarities, they are compared with the corresponding ground-truth similarities obtained from DrugSimDB, a well-known drug-drug similarity tool that is based on drug-centric data. The results provide evidence on the feasibility of patient-centric data from social media as a novel source for computing drug-drug similarity. Full article