Selective Tuning Research Articles

A covalent organic frameworks based sensor for adsorptive stripping voltammetric detection of nanomolar dopamine in living mouse brain

Dopamine (DA) is a type of neurotransmitter playing key roles in brain functions, but detection of DA in the brain is challenging because of its nanomolar concentration. Herein we report a strategy using the covalent organic frameworks (COF) modified electrode for highly sensitive and selective detection of DA in the living mouse brain. The unique physiochemical properties and space-confinement effect of ultrasmall nanochannels of COF can regulate the molecular conformation and electrochemical oxidation of DA. In particular, the electrochemically active oxidation intermediates can be stabilized and accumulated in the nanochannels, thus allowing the detection of nanomolar DA by adsorptive stripping analysis with the limit of detection improved by ∼103 fold in comparison with the conventional cyclic voltammetry. Additionally, thanks to the remarkable difference in adsorption energies of other structurally similar neurotransmitters, the COF modified electrode also displays an excellent selectivity to DA. Finally, the modified electrode was combined with microdialysis to successfully quantify DA in the normal and Parkinson’s disease model mice brain. We believe that COF with tunable selectivity will offer enormous promise for detection of different neurotransmitters.

Adsorption and Thermal Evolution of the Carbonyl‐Functionalized Ionic Liquid [5‐oxo‐C6C1Im][NTf2] on Pt(111): A Combined IRAS, STM, and DFT Study

The coating of heterogeneous catalysts with ionic liquids enables precise tuning of catalytic activity and selectivity. Recently, the fundamentals of solid catalysts with ionic liquid layers have been extensively studied. So far, investigations have focused on simple ILs without specialized functional groups. In our current work, we aim to involve functionalized ILs to take advantage of the interactions between these functional groups, the catalyst, and the reactants. In this study, we investigated the interaction, and thermal stability of the carbonyl‐functionalized IL [5‐oxo‐C6C1Im][NTf2] on Pt(111) by infrared reflection absorption spectroscopy and scanning tunneling microscopy. In addition, we performed density functional theory calculations to support our interpretation. At 200 K and low coverage, the carbonyl group of the [5‐oxo‐C6C1Im]+ cation is oriented parallel to the Pt(111) surface. With increasing coverage, the alkyl chain detaches from the surface and orients towards the vacuum. The [NTf2]‐ anion adsorbs parallel to the surface via the oxygen atoms of the SO2 groups. At higher coverage, at least one of the SO2 groups completely detaches from the surface. Upon heating to 250 K, we observe decomposition and partial desorption of [5‑oxo‐C6C1Im][NTf2], with further decomposition and desorption occurring between 350 and 400 K.

Prediction of Myocardial Infarction Complications using Gradient Boosting

Cardiovascular diseases (CVDs) are the leading cause of death worldwide, representing a significant public health challenge. Myocardial Infarction (MI), a severe manifestation of CVDs, contributes substantially to these fatalities. Machine learning holds great promise for predicting MI. This study explores the potential of Gradient Boosting (GB) techniques for this purpose, explicitly focusing on CatBoost, LightGBM, XGBoost, and XGBoost Random Forest. The study leverages GB's embedded feature selection, missing-value handling, and hyperparameter tuning capabilities. Performance was evaluated using multiple metrics: Area Under the Curve (AUC), classification accuracy, F1 score, precision, recall, and Matthews Correlation Coefficient (MCC). A probabilistic comparison matrix was used to assess the relative performance of the GB models. The results demonstrate the superiority of CatBoost, achieving a classification accuracy of 94.9%, an AUC of 0.992, a recall of 94.9%, and an MCC of 0.82. The probabilistic comparison further confirms CatBoost's superior performance. These findings contribute to MI prediction, highlighting the predictive potential of the CatBoost algorithm and ultimately aiding the fight against MI to achieve better patient outcomes.

Thiolated hyper-crosslinked tetraphenylborate with tunable selectivity for sequential recovery of Pd and Pt from autocatalyst leachate

Palladium (Pd) and platinum (Pt) recovery is crucial due to their extensive applications, economic value, and limited availability. This study developed a thiolated hyper-crosslinked adsorbent (SH-x-TPB) using a tetraphenylborate-based matrix grafted with sulfonic acids, which were subsequently reduced to thiols (−SH). The SH-x-TPB is highly stable in acidic environments, making it suitable for harsh feed conditions. It is also highly porous (63 %), with a hierarchical structure (91 % mesopores) and a high BET surface area (>400 m2 g−1). SH-x-TPB exhibits exceptionally rapid sorption rates for Pd2+ (983 g mmol−1 hr−1) and Pt4+ (31 g mmol−1 hr−1), with high capacities of 386.96 mg Pd2+ g−1 and 72.59 mg Pt4+ g−1. Characterization indicates that Pd2+ adsorption, typically as square planar PdCl42-, is non-ideal and heterogeneous, involving ligand substitution, stable π-complexation, and reduction to Pd⁰. In contrast, Pt4+ adsorption as octahedral PtCl62- is strictly Langmuir-type and homogeneous, primarily involving Pt4+ reduction to Pt2+ by −SH groups. Sorption is pH- and time-dependent, favoring Pd2+ at pH 1–2 within 10 min and Pt4+ at pH 3–4 within 60 min. Under these conditions, a two-stage sequential recovery process successfully collected Pd2+ first, followed by Pt4+, achieving overall recoveries of 99.37 % and 99.67 %, respectively, while leaving unwanted ions in the leachate. The captured metals can be desorbed with 1 M thiourea/2 M HCl solution, rendering the reactivated SH-x-TPB reusable with consistent performance. The competitive adsorption capacities, selective recovery capabilities, recyclability, and simple fabrication methods of SH-x-TPB make it a promising material for sequential metal recovery applications.

Tubulin glutamylation regulates axon guidance via the selective tuning of microtubule-severing enzymes.

The microtubule cytoskeleton is a major driving force of neuronal circuit development. Fine-tuned remodelling of this network by selective activation of microtubule-regulating proteins, including microtubule-severing enzymes, has emerged as a central process in neuronal wiring. Tubulin posttranslational modifications control both microtubule properties and the activities of their interacting proteins. However, whether and how tubulin posttranslational modifications may contribute to neuronal connectivity has not yet been addressed. Here we show that the microtubule-severing proteins p60-katanin and spastin play specific roles in axon guidance during zebrafish embryogenesis and identify a key role for tubulin polyglutamylation in their functional specificity. Furthermore, our work reveals that polyglutamylases with undistinguishable activities in vitro, TTLL6 and TTLL11, play exclusive roles in motor circuit wiring by selectively tuning p60-katanin- and spastin-driven motor axon guidance. We confirm the selectivity of TTLL11 towards spastin regulation in mouse cortical neurons and establish its relevance in preventing axonal degeneration triggered by spastin haploinsufficiency. Our work thus provides mechanistic insight into the control of microtubule-driven neuronal development and homeostasis and opens new avenues for developing therapeutic strategies in spastin-associated hereditary spastic paraplegia.

Utility of Immobilized Metal Salens as Electrocatalysts: Fuel Cells and Organic Electrosynthesis

AbstractThere have been significant advancements in the electrosynthesis of fuels and organic molecules, making it an increasingly sustainable and cost‐effective alternative to traditional chemical redox reagents. Early versions of these systems faced challenges in chemoselectivity due to high applied overpotentials, which have been mitigated with the introduction of molecular electrocatalysts, like metal salens (MSalens). These MSalens reduce the required overpotentials, increase turnover numbers (TON), and have simple modularity within their ligand structure allowing for tunable selectivity. While these MSalen electrocatalysts are typically used homogeneously for engineering simplicity, downstream separations are often costly and time‐consuming. Immobilization of MSalens addresses these issues by enabling synthesis at lower potentials, achieving high selectivity, and facilitating straightforward separations. This review explores the application of MSalens in electrosynthesis and immobilized molecular electrocatalysts in organic electrosynthesis.

Nanostructured Ceria‐Niobia Catalyst for Selective Synthesis of N‐benzylideneanilines

The shape and structure engineering of metal oxide nanomaterials are the potential strategies to optimize surface‐active sites with tunable selectivity for heterogeneous catalysis. This work reports the synthesis of two types of nanostructured CeO2‐Nb2O5 catalysts: (i) one‐pot hydrothermal synthesis of CeO2‐Nb2O5 (CeNb2O5‐HTS) and (ii) CeO2 impregnation on hydrothermally synthesized Nb2O5 nanorods (CeNb2O5‐WI) to elucidate the role of particle shape and CeO2 addition in the structure‐activity efficacy of Nb2O5 nanocatalyst for the selective oxidative C‐N coupling of benzyl alcohol with aniline to produce N‐benzylideneaniline (NBA). The characterization studies showed nanorod morphology of Nb2O5 and high dispersion of CeO2 on Nb2O5 nanorods in the CeNb2O5‐WI catalyst with strong acidic sites and more oxygen vacancies. Consequently, a significantly enhanced catalytic activity was achieved with CeNb2O5‐WI nanocatalyst in the coupling of benzyl alcohol and aniline with 96% yield to NBA, whereas 62% conversion of aniline with 92% selectivity to NBA was obtained with pure Nb2O5 nanorods. In contrast, the CeNb2O5‐HTS catalyst gave 37% conversion of aniline only. The versatile efficiency of the CeNb2O5‐WI nanocatalyst is showcased by synthesizing various functional NBA products. The CeNb2O5‐WI catalyst can be recycled 5 times without much variation in NBA selectivity by achieving reasonably good conversion of aniline.

Optimizing flexural strength of RC beams with recycled aggregates and CFRP using machine learning models.

This paper investigates the flexural bearing behavior of reinforced concrete beams through experimental analysis and advanced machine learning predictive models. The primary problem centers around understanding how varying compositions of construction materials, particularly the inclusion of recycled aggregates and carbon fiber-reinforced polymer (CFRP), affect the structural performance of concrete beams. Eight beams, including those with natural aggregates, recycled aggregates, fly ash, and CFRP, were tested. The study employs state-of-the-art machine learning frameworks, including Random Forest Regressor (RFR), XGBoost (XGB), and LightGBM (LGBM). The formation of these models involved data acquisition from experiments, preprocessing of key input features (such as rebars area, cement portion, recycled and natural aggregate masses, silica fume, fly ash, compressive strength, and CFRP presence), model selection, and hyperparameter tuning using Pareto optimization. The models were then evaluated using performance metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), and coefficient of determination (R2). Outputs focus on load-induced deflection and mid-span displacement. With a dataset of 4851 samples, the optimized models demonstrated excellent performance. The experimental results revealed substantial enhancements in both compressive strength and load-bearing capacity, notably observed in beams incorporating 70% recycled aggregate and 10% silica fume. These beams exhibited a remarkable increase in compressive strength of up to 53.03% and a 7% boost in load-bearing capacity compared to those without recycled aggregate. By integrating experimental analysis with advanced computational techniques, this study advances the understanding of eco-friendly construction materials and their performance, shedding light on the intricate interactions between sustainable construction materials and the flexural bearing behavior of beams.

Hybrid Algorithm Selection and Hyperparameter Tuning on Distribute Machine Learning Resources: Hierarchical Agent-based Approach

Algorithm selection and hyperparameter tuning are critical steps in both academic and applied machine learning (ML). These steps are becoming increasingly delicate due to the extensive rise in the number, diversity, and distributed nature of ML resources. Multi-agent systems, when applied to the design of ML platforms, bring about several distinctive characteristics, such as scalability, flexibility, and robustness, just to name a few. This article proposes a fully automatic and collaborative agent-based mechanism for selecting distributed ML algorithms and simultaneously tuning their hyperparameters. Our method builds upon an existing agent-based hierarchical ML platform and augments its query structure to support the aforementioned functionalities without being limited to specific learning, selection, and tuning mechanisms. We have conducted theoretical assessments, formal verification, and analytical study to demonstrate the correctness, resource utilization, and computational efficiency of our technique. According to the results, our solution is algorithmically correct and exhibits linear time and space complexity in relation to the size of available resources. To further verify its correctness and demonstrate its effectiveness and flexibility across a range of algorithmic options and datasets, the article also presents a series of empirical results on a system composed of 24 algorithms and 9 datasets. The findings not only highlight the efficiency and scalability of the proposed approach, but also show its flexibility and openness to responding to the dynamic and distributed ML ecosystem.

Integration of UAV LiDAR and WorldView-2 images for modeling mangrove aboveground biomass with GA-ANN wrapper

BackgroundIntegrating optical and LiDAR data is crucial for accurately predicting aboveground biomass (AGB) due to their complementarily essential characteristics. It can be anticipated that this integration approach needs to deal with an expanded set of variables and scale-related challenges. To achieve satisfactory accuracy in real-world applications, further exploration is needed to optimize AGB models by selecting appropriate scales and variables.MethodsThis study examined the impact of LiDAR point cloud-derived metrics on estimation accuracies at different scales, ranging from 2 to 16 m cell sizes. We integrated WorldView-2 imagery with LiDAR data to construct biomass models and developed a genetic algorithm-based wrapper for variable selection and parameter tuning in artificial neural networks (GA-ANN wrapper).ResultsOur findings indicated that the highest accuracies in estimating AGB were yielded by 4 m and 6 m cell sizes, followed by 8 m and 10 m, associated with the dimensions of vegetation canopies and sampling plots. Models integrating WorldView-2 and LiDAR data outperformed those using each data source individually, reducing RMSEr by 5.80% and 3.89%, respectively. Combining these data sources can capture the canopy spectral responses and vertical vegetation structure. The GA-ANN wrapper model decreased RMSEr by 1.69% over the ANN model and dwindled the number of variables from 38 to 9. The selected variables included vegetation density, height, species, and vegetation indices.ConclusionsThe appropriate cell size for AGB estimation should consider the sizes of vegetation canopies, tree densities, and sampling plots. The GA-ANN wrapper effectively reduced variables and achieved the highest accuracy. Additionally, canopy spectral and vertical structure information are vital for accurate AGB estimation. Our study offered insights into optimizing mangrove AGB models by integrating optical and LiDAR data. The approach, data, model, and indices employed in this research can effectively predict AGB estimates of any other forest types or vegetation cover types in different climate regions.

Coupling Carbon Dioxide and Cyclohexane Oxide Using Metal-Free Catalyst with Tunable Selectivity of Product Under Mild Conditions

Coupling Carbon Dioxide and Cyclohexane Oxide Using Metal-Free Catalyst with Tunable Selectivity of Product Under Mild Conditions

Automatic Conditioning of Marine Seismic Angle Stack Data With a Convolutional Neural Network

Misalignment of reflections is a common problem in migrated prestack seismic data, which occurs due to moveout correction with incomplete knowledge of the velocity model. This issue persists in partial angle stack data often used for amplitude versus offset (AVO) analyses, and is traditionally treated with residual moveout and trim static corrections. However, these methods require time-consuming velocity selection and parameter tuning, and commonly lead to spurious alignment of reflections with noise. Therefore, we train a convolutional neural network (CNN) on synthetic examples to automatically perform conditioning and alignment of angle stack data. First, two-dimensional synthetic common depth point (CDP) gathers are created using a convolutional modeling method, and then made into input-target pairs where the inputs are poorly moveout-corrected (using inaccurate normal moveout velocities) and the targets are accurately moveout-corrected. These input-target examples are split into angle stacks for the near, mid, and far offsets, and then used to train a CNN to transform the misaligned angle stacks into their more-aligned counterparts. In testing, the trained network increases the alignment of unseen synthetic data, improving the correlation with the target far offset trace from 0.76 to 0.85 on average. The network is applied on two field examples from offshore Norway with Class 3 and Class 2P AVO responses, respectively. In both cases, the angle stack data predicted by the network shows improved alignment, greater resolution in the far offset stacked section, and increased correspondence to a well-tie synthetic seismogram, all while retaining the AVO responses. The CNN predictions are compared to angle stack data following traditional conditioning (residual moveout and trim static corrections), with the results being of similar or greater quality. This method enables high quality conditioning of angle stack data at a fraction of the time required for conventional methods, and is easily adaptable to different datasets.

Hyperparameter Tuning of EfficientNet Method for Optimization of Malaria Detection System Based on Red Blood Cell Image

Nowadays, malaria has become an infectious disease with a high mortality rate. One way to detect malaria is through microscopic examination of blood preparations, which is done by experts and often takes a long time. With the development of deep learning technology, the observation of blood cell images infected with malaria can be more easily done. Therefore, this study proposes a red blood cell image-based malaria detection system using the EfficientNet method with hyperparameter tuning. There are three parameters which are learning rate, activation function, and optimiser. The learning rate used is 0.01 and 0.001, while the activation functions used are ReLU and Tanh. In addition, the optimisers used include Adam, SGD, and RMSProp. In the implementation, the cell image dataset from the NIH repository was pre-processed such as resizing, rotating, filtering, and data augmentation. Then the data is trained and tested on several EfficientNet models (B0, B1, B3, B5, and B7) and their performance values are compared. Based on the test results, EfficientNet-B5 and B7 models showed the best performance compared to other EfficientNet models. The most optimal system test results are when the EfficientNet B5 model is used with a learning rate of 0.001, ReLU activation function, and Adam optimiser, with values of 97.69% (accuracy), 98.36% (precision), and 97.03% (recall). This research has proven that proper model selection and hyperparameter tuning can maximise the performance of cell image-based malaria detection system. The development of this EfficientNet-based diagnostic method is more sensitive and specific in malaria detection using RBCs.

Phase-transformable metal-organic polyhedra for membrane processing and switchable gas separation

The capability of materials to interconvert between different phases provides more possibilities for controlling materials’ properties without additional chemical modification. The study of state-changing microporous materials just emerged and mainly involves the liquefication or amorphization of solid adsorbents into liquid or glass phases by adding non-porous components or sacrificing their porosity. The material featuring reversible phases with maintained porosity is, however, still challenging. Here, we synthesize metal-organic polyhedra (MOPs) that interconvert between the liquid-glass-crystal phases. The modular synthetic approach is applied to integrate the core MOP cavity that provides permanent microporosity with tethered polymers that dictate the phase transition. We showcase the processability of this material by fabricating a gas separation membrane featuring tunable permeability and selectivity by switching the state. Compared to most conventional porous membranes, the liquid MOP membrane particularly shows the selectivity for CO2 over H2 with enhanced permeability.

Temporal cross‐validation in forecasting: A case study of COVID‐19 incidence using wastewater data

AbstractTwo predominant methodologies in forecasting temporal processes include traditional time series models and machine learning methods. This paper investigates the impact of time series cross‐validation (TSCV) on both approaches in the context of a case study predicting the incidence of COVID‐19 based on wastewater data. The TSCV framework outlined in the paper begins by engineering interpretable features hypothesized as potential predictors of COVID‐19 incidence. Feature selection and hyperparameter tuning are then utilized with TSCV to identify the best features and hyperparameters for optimal model performance given a specific forecast horizon. While evidence supporting the utility of TSCV for auto‐regressive integrated moving average model with exogenous variables (TS‐ARIMAX) forecasts is lacking in this study, such an approach proves advantageous for gradient boosting machine forecasts (TS‐GBM). In Wyoming, for instance, TS‐GBM had a 34.9% improvement compared to naïve predictions, whereas GBM without TSCV only had a 15.6% improvement. However, TSCV also enhances interpretability for both TS‐ARIMAX and TS‐GBM models as this approach selects specific features, such as lagged values of COVID‐19 cases, based on forecast performance and forecast length. Future research should work to explore the influence of stationarity and model averaging on the performance of TSCV in forecasting applications.

Interpenetrating Polymer Network Hydrogels with Tunable Viscoelasticity and Proteolytic Cleavability to Direct Stem Cells In Vitro.

The dynamic nature of cellular microenvironments, regulated by the viscoelasticity and enzymatic cleavage of the extracellular matrix, remains challenging to emulate in engineered synthetic biomaterials. To address this, a novel platform of cell-instructive hydrogels is introduced, composed of two concurrently forming interpenetrating polymer networks (IPNs). These IPNs consist of the same basic building blocks - four-armed poly(ethylene glycol) and the sulfated glycosaminoglycan (sGAG) heparin - are cross-linked through either chemical or physical interactions, allowing for precise and selective tuning of the hydrogel's stiffness, viscoelasticity, and proteolytic cleavability. The studies of the individual and combined effects of these parameters on stem cell behavior revealed that human mesenchymal stem cells exhibited increased spreading and Yes-associated protein transcriptional activity in more viscoelastic and cleavable sGAG-IPN hydrogels. Furthermore, human induced pluripotent stem cell (iPSC) cysts displayed enhanced lumen formation, growth, and pluripotency maintenance when cultured in sGAG-IPN hydrogels with higher viscoelasticity. Inhibition studies emphasized the pivotal roles of actin dynamics and matrix metalloproteinase activity in iPSC cyst morphology, which varied with the viscoelastic properties of the hydrogels. Thus, the introduced sGAG-IPN hydrogel platform offers a powerful methodology for exogenous stem cell fate control.

Novel sol-gel derived layered double oxides and layered double oxide/γ-Al2O3 with tunable selectivity as promising adsorbents for L-lactate uptake from the myoblast culture medium

Cultured meat production, a biotechnological solution for global protein demand and sustainability, faces economic challenges due to the high demand for cell culture medium. Contamination with cell metabolites, particularly L-lactate, impedes myoblast proliferation in high-density suspension culture. Eliminating L-lactate is crucial for reusing the medium and overcoming economic barriers in mass myoblast culture. Retaining essential nutrients like D-glucose, amino acids, and vitamins after L-lactate removal is imperative for sustained myoblast growth. This study proposes a sustainable and economically feasible adsorption technique utilizing novel sol-gel derived Mg-Al layered double oxides and Mg-Al layered double oxide/γ-Al2O3 with tunable selectivity as a promising tool for L-lactate uptake from the myoblast medium. In an aqueous solution, L-lactate uptake and selectivity over D-glucose were enhanced with the decrease in total Mg/Al ratio and crystallinity, increase in Al2O3 dispersion in adsorbent, specific surface area, and porosity. The latter was achieved successfully by metal alkoxide sol-gel method employing an organic structure-directing agent, where LDO/amorphous alumina nanohybrid with Mg/Al = 1.23 was successfully prepared in mixed methanol-ethanol solution in a relatively short time. A simple mixture of Mg-Al LDO with Mg/Al = 2 and nano-γ-Al2O3 prepared by a sustainable and economically feasible co-precipitation method was found to have comparable efficiency and selectivity to a costly sol-gel derived material. In myoblast medium, lower total Mg/Al was associated with higher cytocompatibility, pH-stability, and selectivity, while surface properties of materials did not play a significant role. Nano-γ-Al2O3 was identified as the most promising material for selective L-lactate uptake from the myoblast culture medium. Thus, further optimization of the medium treatment process with nano-γ-Al2O3 can realize cost-effective high-density myoblast culture with circular use of the medium – a novel sustainable process in the biotechnology field.

Controllable Regulation of CO2 Adsorption Behavior via Precise Charge Donation Modulation for Highly Selective CO2 Electroreduction to Formic Acid.

The synthesis of value-added products via CO2 electroreduction (CO2ER) is of great significance, but the development of efficient and versatile strategies for the controllable selectivity tuning is extremely challenging. Herein, the tuning of CO2ER selectivity through the modulation of CO2 adsorption behavior is proposed. Using the constructed zeolitic MOF (SNNU-339), CO2 adsorption behavior is controllably changed from *CO2 to CO2* via the precise ligand-to-metal charge donation (LTMCD) regulation. It is confirmed that the high electronegativity of the coordinate ligand directly restricts the LTMCD, reduces the charge density on the metal sites, lowers the Gibbs free energy for CO2* adsorption, and leads to the transformation of CO2 adsorption mode from *CO2 to CO2*. Owing to the modulated CO2 adsorption behavior and regulated kinetics, SNNU-339 exhibits superior HCOOH selectivity (≈330% promotion, 85.6% Faradaic efficiency) and high CO2ER activity. The wide applicability of the proposed approach sheds light on the efficient CO2ER. This study provides a competitive strategy for rational catalyst design and underscores the significance of adsorption behavior tuning in electrocatalysis.

Feature Extraction and Identification of Rheumatoid Nodules Using Advanced Image Processing Techniques

Background/Objectives: Accurate detection and classification of nodules in medical images, particularly rheumatoid nodules, are critical due to the varying nature of these nodules, where their specific type is often unknown before analysis. This study addresses the challenges of multi-class prediction in nodule detection, with a specific focus on rheumatoid nodules, by employing a comprehensive approach to feature extraction and classification. We utilized a diverse dataset of nodules, including rheumatoid nodules sourced from the DermNet dataset and local rheumatologists. Method: This study integrates 62 features, combining traditional image characteristics with advanced graph-based features derived from a superpixel graph constructed through Delaunay triangulation. The key steps include image preprocessing with anisotropic diffusion and Retinex enhancement, superpixel segmentation using SLIC, and graph-based feature extraction. Texture analysis was performed using Gray-Level Co-occurrence Matrix (GLCM) metrics, while shape analysis was conducted with Fourier descriptors. Vascular pattern recognition, crucial for identifying rheumatoid nodules, was enhanced using the Frangi filter. A Hybrid CNN–Transformer model was employed for feature fusion, and feature selection and hyperparameter tuning were optimized using Gray Wolf Optimization (GWO) and Particle Swarm Optimization (PSO). Feature importance was assessed using SHAP values. Results: The proposed methodology achieved an accuracy of 85%, with a precision of 0.85, a recall of 0.89, and an F1 measure of 0.87, demonstrating the effectiveness of the approach in detecting and classifying rheumatoid nodules in both binary and multi-class classification scenarios. Conclusions: This study presents a robust tool for the detection and classification of nodules, particularly rheumatoid nodules, in medical imaging, offering significant potential for improving diagnostic accuracy and aiding in the early identification of rheumatoid conditions.

Optimizing Machine Learning-Based Intrusion Detection Systems for Enhanced Security in Cloud Computing Environments.

In today’s cloud computing environments, robust network security is crucial due to the inherently distributed and dynamic nature of cloud systems. Traditional Network Intrusion Detection Systems (NIDS) often face challenges in handling large-scale, rapidly evolving data and sophisticated attack vectors unique to cloud settings. This paper presents an optimized Machine Learning (ML)-based NIDS framework designed specifically for cloud infrastructures, leveraging feature selection, dimensionality reduction, and algorithmic tuning techniques to enhance detection accuracy and reduce false positives. Integrating supervised and unsupervised learning methods, this NIDS system can detect both known and novel attack types efficiently. By utilizing cloud-specific datasets and real-time traffic monitoring, it adapts well to the scalability and elasticity requirements of cloud environments. Additionally, the system incorporates automated optimization techniques, such as hyperparameter tuning and ensemble learning, to further enhance performance. Experimental results show improvements in detection rates, reduced computational overhead, and better scalability, making it a promising solution for modern cloud-based infrastructures.