Search Results (472)

Background: Peptides are a class of molecules that can be presented as good antimicrobials and with mechanisms that avoid resistance, and the design of peptides with good activity can be complex and laborious. The study of their quantitative structure–activity relationships through machine learning algorithms can shed light on a rational and effective design. Methods: Information on the antimicrobial activity of peptides was collected, and their structures were characterized by molecular descriptors generation to design regression and classification models based on machine learning algorithms. The contribution of each descriptor in the generated models was evaluated by determining its relative importance and, finally, the antimicrobial activity of new peptides was estimated. Results: A structured database of antimicrobial peptides and their descriptors was obtained, with which 56 machine learning models were generated. Random Forest-based models showed better performance, and of these, regression models showed variable performance (R² = 0.339–0.574), while classification models showed good performance (MCC = 0.662–0.755 and ACC = 0.831–0.877). Those models based on bacterial groups showed better performance than those based on the entire dataset. The properties of the new peptides generated are related to important descriptors that encode physicochemical properties such as lower molecular weight, higher charge, propensity to form alpha-helical structures, lower hydrophobicity, and higher frequency of amino acids such as lysine and serine. Conclusions: Machine learning models allowed to establish the structure–activity relationships of antimicrobial peptides. Classification models performed better than regression models. These models allowed us to make predictions and new peptides with high antimicrobial potential were proposed. Full article

Background: Hypertension is a serious global health issue affecting over one billion adults and leading to severe complications if left unmanaged. Despite medical advancements, only a fraction of patients effectively have their hypertension under control. Among the factors that hinder adherence to hypertensive drugs are the debilitating side effects of the drugs. The lack of adherence results in poorer patient outcomes as patients opt to live with their condition, instead of having to deal with the side effects. Hence, there is a need to discover new hypertension drug molecules with better side effects to increase patient treatment options. To this end, computational methods such as artificial intelligence (AI) have become an exciting option for modern drug discovery. AI-based computational drug discovery methods generate numerous new lead antihypertensive drug molecules. However, predicting their potential side effects remains a significant challenge because of the complexity of biological interactions and limited data on these molecules. Methods: This paper presents a machine learning approach to predict the potential side effects of computationally synthesised antihypertensive drug molecules based on their molecular properties, particularly functional groups. We curated a dataset combining information from the SIDER 4.1 and ChEMBL databases, enriched with molecular descriptors (logP, PSA, HBD, HBA) using RDKit. Results: Gradient Boosting gave the most stable generalisation, with a weighted F1 of 0.80, and AUC-ROC of 0.62 on the independent test set. SHAP analysis over the cross-validation folds showed polar surface area and logP contributing the largest global impact, followed by hydrogen bond counts. Conclusions: Functional group patterns, augmented with key ADMET descriptors, offer a first-pass screen for identifying side-effect risks in AI-designed antihypertensive leads. Full article

This paper introduces a hierarchical object-centric descriptor framework called TOSD (Triplet Object-Centric Semantic Descriptor). The goal of this method is to overcome the limitations of existing pixel-based and global feature embedding approaches. To this end, the framework adopts a hierarchical representation that is explicitly designed for multi-level reasoning. TOSD combines shape, color, and topological information without depending on predefined class labels. The shape descriptor captures the geometric configuration of each object. The color descriptor focuses on internal appearance by extracting normalized color features. The topology descriptor models the spatial and semantic relationships between objects in a scene. These components are integrated at both object and scene levels to produce compact and consistent embeddings. The resulting representation covers three levels of abstraction: low-level pixel details, mid-level object features, and high-level semantic structure. This hierarchical organization makes it possible to represent both local cues and global context in a unified form. We evaluate the proposed method on multiple vision tasks. The results show that TOSD performs competitively compared to baseline methods, while maintaining robustness in challenging cases such as occlusion and viewpoint changes. The framework is applicable to visual odometry, SLAM, object tracking, global localization, scene clustering, and image retrieval. In addition, this work extends our previous research on the Semantic Modeling Framework, which represents environments using layered structures of places, objects, and their ontological relations. Full article

Lightweight speech denoising models have made remarkable progress in improving both speech quality and computational efficiency. However, most models rely on long temporal windows as input, limiting their applicability in low-latency, real-time scenarios on edge devices. To address this challenge, we propose a lightweight hybrid module, Temporal Statistics Enhancement, Squeeze-and-Excitation-based Dual Convolutional Attention, and Band-wise Attention (TSE, SDCA, BA) Module. The TSE module enhances single-frame spectral features by concatenating statistical descriptors—mean, standard deviation, maximum, and minimum—thereby capturing richer local information without relying on temporal context. The SDCA and BA module integrates a simplified residual structure and channel attention, while the BA component further strengthens the representation of critical frequency bands through band-wise partitioning and differentiated weighting. The proposed model requires only 0.22 million multiply–accumulate operations (MMACs) and contains a total of 112.3 K parameters, making it well suited for low-latency, real-time speech enhancement applications. Experimental results demonstrate that among lightweight models with fewer than 200K parameters, the proposed approach outperforms most existing methods in both denoising performance and computational efficiency, significantly reducing processing overhead. Furthermore, real-device deployment on an improved hearing aid confirms an inference latency as low as 2 milliseconds, validating its practical potential for real-time edge applications. Full article

This study investigates how lighting conditions influence emotional and neural responses in a standardized, simulated museum environment. A multimodal evaluation framework combining subjective and objective measures was used. Thirty-two international students assessed their viewing experiences using 14 semantic differential descriptors, while real-time EEG signals were recorded via the EMOTIV EPOC X device. Spectral energy analyses of the α, β, and θ frequency bands were conducted, and a θα energy ratio combined with γ coefficients was used to model attention and comfort levels. The results indicated that high illuminance (300 lx) and high correlated color temperature (4000 K) significantly enhanced both attention and comfort. Art majors showed higher attention levels than engineering majors during short-term viewing. Among four regression models, the backpropagation (BP) neural network achieved the highest predictive accuracy (R² = 88.65%). These findings provide empirical support for designing culturally inclusive museum lighting and offer neuroscience-informed strategies for promoting the global dissemination of traditional Chinese culture, further supported by retrospective interview insights. Full article

The ability to predict capacity retention is critical for ensuring the long-term reliability of supercapacitors in energy storage systems. This study presents a comprehensive machine learning framework that integrates both electrical cycling data and experimentally derived material and structural features to forecast the degradation behavior of commercial supercapacitors. A total of seven supercapacitor samples were tested under various current and voltage conditions, resulting in over 70,000 charge–discharge cycles across three case studies. In addition to electrical measurements, detailed physical and material characterizations were performed, including electrode dimension analysis, Scanning Electron Microscopy (SEM), Energy Dispersive X-ray Spectroscopy (EDS), and Thermogravimetric Analysis (TGA). Three machine learning models, Linear Regression (LR), Random Forest (RF), and Multi-Layer Perceptron (MLP), were trained using both cycler-only and combined cycler + material features. Results show that incorporating material features consistently improved prediction accuracy across all models. The MLP model exhibited the highest performance, achieving an R² of 0.976 on the training set and 0.941 on unseen data. Feature importance analysis confirmed that material descriptors such as porosity, thermal stability, and electrode thickness significantly contributed to model performance. This study demonstrates that combining electrical and material data offers a more holistic and physically informed approach to supercapacitor health prediction. The framework developed here provides a practical foundation for accurate and robust lifetime forecasting of commercial energy storage devices, highlighting the critical role of material-level insights in enhancing model generalization and reliability. Full article

To solve the problem of the limited capability of multimodal image feature descriptors constructed by gradient information and the phase consistency principle, a method of cumulative structure feature descriptor construction with rotation invariance is proposed in this paper. Firstly, we extract the direction of multi-scale and multi-direction feature point edges using the Log-Gabor odd-symmetric filter and calculate the amplitude of pixel edges based on the phase consistency principle. Then, the main direction of the key points is determined based on the edge direction feature map, and the coordinates are established according to the main direction to ensure that the feature point descriptor has rotation invariance. Finally, the Log-Gabor odd-symmetric filter calculates the cumulative structural response in the maximum direction and constructs a highly identifiable descriptor with rotation invariance. We select several representative heterogeneous images as test data and compare the matching performance of the proposed algorithm with several excellent descriptors. The results indicate that the descriptor constructed in this paper is more robust than other descriptors for heterosource images with rotation changes. Full article

ECG monitoring is central to the early detection of cardiac abnormalities. We compared 28 manually selected signal-specific features with 159 automatically extracted signal-independent descriptors from the MIT BIH Arrhythmia Database. ANOVA reduced features to the 10 most informative attributes, which were evaluated alone and in combination with the signal-specific features using Random Forest, SVM, and deep neural networks (CNN, RNN, ANN, LSTM) under an interpatient 80/20 split. Merging the two feature groups delivered the best results: a 128-layer CNN achieved 100% accuracy. Power profiling revealed that deeper models improve accuracy at the cost of runtime, memory, and CPU load, underscoring the trade-off faced in edge deployments. The proposed hybrid feature strategy provides beat-by-beat classification with a reduction in the number of features, enabling real-time ECG screening on wearable and IoT devices. Full article

Background: The aging population is increasing, leading to a greater need for home care for older adults, often provided by informal caregivers (ICs). These caregivers face numerous challenges, requiring adequate training and support. Objectives: This study aimed to map the main interventions performed by the Rehabilitation Nursing Specialist in empowering ICs of older adults at home. Methods: A scoping review was conducted following the Joanna Briggs Institute methodology. The search included seven articles published between 2019 and 2024, in Portuguese, English, and Spanish, available in the PubMed e CINHAL Ultimate databases. The descriptors used were (Rehabilitation Nursing) AND (Informal Caregivers OR Caregivers) AND (Elderly OR Aged) AND (mentoring OR Training. Results: The RNS interventions focused on training caregivers in technical skills (e.g., positioning, transfers, hygiene care, feeding, medication administration), preventing caregiver burden, managing behavioral and psychological symptoms of dementia, promoting self-care, and emotional support. Educational programs and the use of technologies (telehealth) were identified as effective strategies. Conclusions: RNS interventions are crucial for enhancing the skills and well-being of ICs, improving the quality of care provided to older adults at home, and reducing caregiver burden. Person-centered care, continuous support, and recognizing the caregiver’s role are fundamental aspects of these interventions. Full article

Molecular property prediction, as one of the important tasks in cheminformatics, is attracting more and more attention. The structure of a molecule is closely related to its properties, and a symmetrical molecular structure may differ significantly from an asymmetrical structure in terms of properties, such as the melting point, boiling point, water solubility, and so on. However, a single molecular representation does not provide a better overall representation of the molecule. And, it is also a challenge to better use graph neural networks to aggregate the information of neighboring nodes in the molecular graph. So, in this paper, we constructed a novel graph neural network with additive attention (termed Add-GNN) for molecular property prediction, which fuses the molecular graph and molecular descriptors to jointly represent molecular features in order to make the molecular representations more comprehensive. Then, in the message-passing stage, we designed an additive attention mechanism that can effectively fuse the features of neighboring nodes and the features of edges to better capture the intrinsic information of molecules. In addition, we applied L2-norm to calculate the importance of each atom to the predicted results and visualized it, providing interpretability to the model. We validated the proposed model on public datasets and showed that the model outperforms graph-based baseline methods and some graph neural network variants, proving that our proposed method is feasible and competitive. Full article

The genus Musa L. is one of the most important genera worldwide due to its use in food as a source of carbohydrates. A morphological characterization was performed to evaluate the potential of 100 accessions of Musa spp. from the Amazon region of Ecuador, applying 73 qualitative and quantitative descriptors in addition to the ecogeographic characterization. The multivariate analyses identified four large groups: The first is composed of the Musa AAB Simmonds ecotype “Hartón Plantain” and the “Cuerno Clone”. The second group is composed of the Musa acuminata Colla ecotype “Orito”. The third group is composed of the Musa acuminata ecotype “Malay plantain or red plantain”; and the fourth group is composed of the Musa × paradisiaca L. AAB ecotype “Barraganete” and banana or banana materials and the Musa AAB Simmonds ecotype “Plátano Dominico”. The qualitative descriptors with the highest discriminant value were the shape of the ♂ floret bud, the appearance of the rachis, and the pigmentation of the compound tepal, and the quantitative discriminant characters were the height of the pseudostem, the length of the leaf blade, the width of the leaf blade, and the weight of the raceme. The analysis with CAPFITOGEN of these 100 accessions through the ecogeographic characterization map identified 23 categories, highlighting category 20 with a coverage of 40.35%, which mainly includes the provinces of Orellana, Sucumbíos, part of Napo, Pastaza, and Morona Santiago. This category occurs within an annual temperature range between 21.6 °C and 27 °C, an apparent density of 1.25 to 1.44 g cm⁻³, and a cation exchange capacity (CEC) of 4 to 29 Cmol kg⁻¹. The morphological characterization of 100 Musa accessions revealed significant phenotypic variability, with four distinct morphological groups identified through cluster analysis. Key differences were observed in traits such as bunch weight, fruit length, and vegetative vigor. This variability highlights the potential of certain accessions for use in genetic improvement programs. The findings contribute valuable information for the efficient conservation, selection, and utilization of the Musa germplasm in Ecuadorian agroecosystems. The results demonstrate the existence of an important genetic variability in the INIAP Musa Germplasm Bank in the Ecuadorian Amazon region. Full article

Background: The toxicity of pesticides for fish in general and Rainbow Trout (Oncorhynchus mykiss) in particular is an important ecological indicator required by regulations, and it implies the use of a large number of fish. The number of animals needed would be even higher to evaluate metabolites and pesticide impurities. Considering ethical issues, the costs, and the necessary resources, the use of in silico models is often proposed. Aim of the study: We explore the use of advanced Monte Carlo methods to obtain improved results for models testing Rainbow Trout (Oncorhynchus mykiss) acute toxicity. Several versions of the stochastic Monte Carlo simulation of pesticide toxicity for Rainbow Trout, carried out using CORAL software, were studied. The set of substances was split into four subsets: active training, passive training, calibration, and validation. Modeling was repeated five times to enable better statistical evaluation. To improve the predictive potential of models, the index of ideality of correlation (IIC), correlation intensity index (CII), and coefficient of conformism of correlation prediction (CCCP) were applied. Main results and novelty: The most suitable results were observed in the case of the CCCP-based optimization for SMILES-based descriptors, achieving an R² of 0.88 on the validation set, in all five random splits, demonstrating consistent and robust modeling performance. The relationship of information systems related to QSAR simulation and new ideas is discussed, assigning a key role to fundamental concepts like mass and energy. The study of the mentioned criteria of predictive potential during the conducted computer experiments showed that even though they are all aimed at improving the predictive potential, their values do not correlate, except for the CII and the CCCP. This means that, in general, the information impact of the considered criteria has a different nature, at least in the case of the simulation of toxicity for Rainbow Trout (Oncorhynchus mykiss). The applicability domain of the model is specific for pesticides; the software identifies potential outliers by looking at rare molecular fragments. Full article

One of the quintessential goals of musical instrument acoustics is to improve the perceived sound produced by, e.g., a violin. To achieve this, the connections between physical (mechanical and geometrical) properties and perceived sound output need to be understood. In this article, a single facet of this complex problem will be discussed using experimental results obtained for six violins of varying back arch height. This is the first investigation of its kind to focus on back arch height. It may serve to inform instrument makers and researchers alike about the variation in sound that can be achieved by varying this parameter. The test instruments were constructed using state-of-the-art methodology to best represent the theoretical case of changing back arch height on a single instrument. Three values of back arch height ($12.1$, $14.8$ and $17.5$ mm) were investigated. The subsequent perceptual tests consisted of a free sorting task in the playing situation and three two-alternative forced choice listening tests. The descriptors “round” and “warm” were found to be linked to back arch height. The trend was non-linear, meaning that both low- and high-arch height instruments were rated as possessing more of these descriptors than their medium-arch height counterparts. Additional results were obtained using stimuli created by hybrid synthesis. However, these could not be linked to those using real playing or recordings. The results of this study serve to inform violin makers about the relative importance of back arch height and its specific influence on sound output. The discussion of the applied methodology and interpretation of results may serve to inform researchers about important new directions in the field of musical instrument acoustics. Full article

As a knowledge-intensive activity, the Kansei engineering (KE) process encounters numerous challenges in the design knowledge flow, primarily due to issues related to information reliability, uncertainty, and subjectivity. Bridging this gap, this study introduces an advanced KE framework integrating a cloud model with Z-numbers (CMZ) and Bayesian elastic net regression (BENR). In stage-I of this KE, data mining techniques are employed to process online user reviews, coupled with a similarity analysis of affective word clusters to identify representative emotional descriptors. During stage-II, the CMZ algorithm refines K-means clustering outcomes for market-representative product forms, enabling precise feature characterization and experimental prototype development. Stage-III addresses linguistic uncertainties in affective modeling through CMZ-augmented semantic differential questionnaires, achieving a multi-granular representation of subjective evaluations. Subsequently, stage-IV employs BENR for automated hyperparameter optimization in design knowledge inference, eliminating manual intervention. The framework’s efficacy is empirically validated through a domestic cleaning robot case study, demonstrating superior performance in resolving multiple information processing challenges via comparative experiments. Results confirm that this KE framework significantly improves uncertainty management in design knowledge flow compared to conventional implementations. Furthermore, by leveraging the intrinsic symmetry of the normal cloud model with Z-numbers distributions and the balanced ℓ₁/ℓ₂ regularization of BENR, CMZ–BENR framework embodies the principle of structural harmony. Full article

This study addresses the side effect of the rapid development of the Internet, positioning botnets within digital ecosystems as a very serious potential threat to the Internet users. Malicious web robot might facilitate Web/data scraping, DDoS attacks, and data theft yielding serious cybersecurity threats. Modern botnets are advanced and have unique browser fingerprints, making their detection a real challenge. Traditional feature extraction methods heavily depend on expert knowledge. They also struggle with dimensional inconsistency when processing sessions of varying lengths, failing to counter evolving camouflage attacks. To approach such challenges, we propose Session2vec, a session representation framework based on multi-instance learning (MIL), which pioneers the MIL approach for Web session modeling. In this approach, we treat each request as an instance and the entire session as an instance collection, and then we use the FastText model to convert each URL request into a vector representation. Then, we utilize two innovative multi-instance aggregation methods: SARD (Session-level Aggregated Residual Descriptors) and SFAR (Session-level Fisher Aggregated Representation) to aggregate variable-length sessions into fixed-dimensional vectors capturing spatiotemporal features and distributional information within sessions. Simulation results of the proposed SARD and SFAR methods on public datasets show accuracy improvement of 5.2% and 16.3% on average, respectively, compared to state-of-the-art baselines. They also enhance F1 scores by 8.5% and 19.7%, respectively. Full article