Multilayer Technique Research Articles

Ensemble Technique for Diabetic Precision Medicine Classification

It is precisely 100 years after giving an insulin shot to a human, which created a revolution in diabetes treatment. Since the fate of diabetes patients has changed in humankind. In this regard, the exact dosage and same set of medicine for diabetes patients may not fit. Thus, there is a requirement for Precision medicine which can change the treatment of diabetes. There is a requirement for building automated intelligent systems to recommend precision medicine that can help practitioners. This paper discusses precision medicine, which has a complete schema for deriving Precision medicine from Big data. In our proposed schema, the component Intelligent Precision Medicine Engine, a new phase is added to filter the non-diabetic patient records to be processed by the Recommender engine, which would reduce the computational energies. With this object, a multi-layered bagging technique is used to classify with the best result nearing 96% with the UCI machine learning dataset for diabetes. Three layers of classification multi-models with majority voting are designed, and results are discussed.

The temporal inverted internal limiting membrane flap technique versus multilayered inverted flap technique in patients with idiopathic macular hole

Objectives This study aimed to compare the temporal inverted internal limiting membrane (ILM) flap technique with the multilayered inverted ILM flap technique for treating idiopathic macular holes (IMHs) by assessing anatomical outcomes using optical coherence tomography (OCT) and functional outcomes through best corrected visual acuity (BCVA) and optical coherence tomography angiography (OCTA). Background ILM flaps act as a scaffold that promotes macular hole closure by facilitating cell proliferation and migration. Patients and methods Patients with IMHs were divided into two groups. Group A underwent the temporal inverted ILM flap technique, while group B received the multilayered inverted ILM flap technique. Preoperative assessment of BCVA, OCT and OCTA. Follow-up at 1, 3, and 6 months by OCT and assessment of BCVA, and OCTA at 3 months. Results The study included 20 eyes with IMH: group A (mean age 60.9±4.51 years) and group B (mean age 62.7±3.74 years). Postoperative OCT revealed no significant differences in closure patterns between the groups. Group A had 60% type U, 10% type V, and 20% type W closure patterns, with 10% of cases failing to close. Group B had 70% type U, 20% type V, and 10% type W closure patterns. BCVA improved from 0.06±0.02 to 0.24±0.14 in group A and from 0.05±0.02 to 0.30±0.11 in group B. Conclusion While no significant anatomical differences were observed between the two techniques, the multilayered inverted ILM flap technique demonstrated superior functional outcomes compared with the temporal flap technique.

Operative technique: Endoscopic transnasal surgery for congenital meningoencephalocele of the anterior skull base.

Congenital meningoencephaloceles of the anterior skull base (ASB) are rare lesions that become evident during childhood and, if not properly diagnosed and treated, can be associated with severe complications. In the past, encephaloceles were treated exclusively with open surgical approaches, which, however, are associated with high complication rates. Recent years have seen the large-scale introduction of transnasal endoscopic approaches to the skull base, and several Authors suggest that endoscopic resection and repair in cases of meningoencephalocele may be the treatment of first choice, being associated with lower complication rates and reduced operative time compared with open procedures. We illustrate step-by-step the transnasal endoscopic treatment of congenital meningoencephalocele and repair of ASB defect by multilayer technique.

Morbidity of multimodal treatments including endoscopic surgery for sinonasal malignancies: Results of an international collaborative study on 940 patients (MUSES).

In the management of sinonasal malignancies treatment-induced morbidity and mortality is gaining relevance both for surgical approaches (endoscopic and open resection) and non-surgical therapies. The aim of this multicenter study is to assess complications associated with endoscopic surgery and non-surgical treatments (neoadjuvant and/or adjuvant) for malignant sinonasal tumors. All patients with nasoethmoidal malignancies treated with curative intent with endoscopic or endoscopic-assisted surgery at three referral centers with uniform management policies were included. Neo- and/or adjuvant (chemo)radiotherapy was administered according to histology and pathological report. Demographics, treatment characteristics, and complications related both to the surgical and non-surgical approaches were retrieved. The data were analyzed with univariate and multivariate statistics to assess independent predictors of complications. Nine hundred and forty patients were included, 643 males (68%) and 297 females (32%). A total of 225 complications were identified in 187 patients (19.9%): cerebrospinal fluid (CSF) leak (3.5%), mucocele (2.3%), surgical site bleeding (2.0%), epiphora (2.0%), and radionecrosis (2.0%) were the most common. Treatment-related mortality was 0.4%. Variables independently associated with complications at multivariate analysis were principally dural resection (OR 1.92), cranioendoscopic or multiportal resection (OR 2.93), dural repair with multilayer technique with less than three layers (OR 2.17), and graft different from iliotibial tract (OR 3.29). Our study shows that modern endoscopic treatments and radiotherapy for sinonasal malignancies are associated with limited morbidity and treatment-related mortality. CSF leak and radionecrosis, although rare, remain the most frequent complications and should be further addressed by future research efforts.

Large-Bandwidth Lithium Niobate Electro-Optic Modulator for Frequency-Division Multiplexing RFID Systems

In the face of increasingly complex application scenarios, there is an urgent need for (Radio Frequency Identification) RFID systems that are capable of accurately identifying microwave signals of different frequency bands. Based on the acumen detection characteristics of microwave signals by lithium niobate electro-optic modulators, applying large-bandwidth thin-film lithium niobate electro-optic modulation to RFID systems can achieve efficient operation across multiple frequency bands. This study discusses, in detail, the design, simulation, fabrication, and testing process of the electro-optic modulator to obtain a high-performance, large-bandwidth lithium niobate electro-optic modulator. By using multilayer lithography techniques to prepare thick traveling-wave electrodes, the problem of irregular cross-sections during the fabrication of thick electrodes has been successfully reduced, improving the stability and controllability of the device. Test results show that the insertion loss of the electro-optic modulator is about 6 dB, the extinction ratio is 36.5 dB, the optical waveguide mode field is 1 μm, the full-band characteristic impedance is 50 Ω, the test bandwidth is 50 GHz, and the half-wave voltage is 1.8 V. Compared with existing optimization schemes, this design not only achieves a large bandwidth and a small half-wave voltage, but also proposes a new fabrication process scheme, optimizing the process and resulting in samples with stable performance.

A Review of the Multilayering Technique of Injecting Dermal Fillers

The multilayer injection technique for dermal fillers has emerged as a promising strategy in facial rejuvenation, aiming to restore volume, enhance contours, and achieve a more natural and youthful appearance by strategically placing fillers of varying rheology in multiple facial planes. This contrasts with more traditional, single-layer injection techniques. This scoping review aims to critically evaluate evidence around the feasibility, procedural approaches, outcomes, and complications associated with the multilayer approach. A review of the literature was conducted across multiple databases, including Medline, Web of Science, and Embase, for studies published between January 1, 2010, and June 4, 2024. The search included keywords related to dermal fillers, facial rejuvenation, and multilayer injection techniques. Experimental studies, including randomized control trials (RCTs), observational studies, retrospective studies, case series, and cadaver studies were considered eligible for review. The search yielded 6 studies that met the inclusion criteria: 2 cadaver studies with associated prospective studies and 4 retrospective reviews. The studies collectively involved 464 patients and 15 human cadavers. The cadaver studies focused on establishing the anatomical justification for the multilayer technique, while the clinical studies reported high patient and physician satisfaction with few complications. The multilayer injection technique is a promising approach to facial rejuvenation, offering natural-looking results with a sound anatomical basis and low risk of complications. However, the existing literature is limited by methodological shortcomings, including variations in study designs, lack of control groups, and reliance on subjective assessments. Further rigorous research is needed to validate the efficacy and safety of this technique in live patient settings.

Forecasting municipal solid waste generation using advanced transformer and multi-layer perceptron techniques

Forecasting municipal solid waste generation using advanced transformer and multi-layer perceptron techniques

MLAD: Manifest and latent anomaly detection based on the integration of reconstruction and MLFP-KNN methods

Abstract In the realm of industrial manufacturing, anomaly detection technologies are essential for enhancing production efficiency. This paper aims to optimize the detection of anomalies in industrial manufacturing settings by introducing a novel framework manifest and latent anomaly detection (MLAD). Firstly, we redefine anomalies as manifest and latent, further subdividing the original categories of structural and logical anomalies. To address the issue of insufficient feature space information utilization in previous reconstruction-based methods, which led to inadequate detection of latent anomalies, we combine a reconstruction-based approach with the multi-layer feature pyramid k-nearest neighbors technique. Additionally, we introduce a Hybrid Attention mechanism to refine the autoencoder’s reconstruction process, thereby enhancing the detection of latent anomalies and increasing overall accuracy. Our experiments on the MVTec LOCO AD dataset demonstrate that MLAD achieves a significant improvement in anomaly detection, with an Image-level AUROC score of 90.8% and Pixel-level AU-sPRO of 79.3%. The integration of the Hybrid Attention mechanism significantly boosts the precision of anomaly detection, highlighting the effectiveness of our approach in enhancing industrial anomaly detection capabilities. The framework provides a more nuanced understanding of industrial defects, contributing valuable insights and practical improvements to the field of industrial anomaly detection.

MLP neural networks for compressive strength assessment of AFRP-confined concrete

Several researchers are interested in the prediction of the compressive strength of fiber reinforced polymers confined concrete. For this purpose, many linear and nonlinear regression equations were elaborated. Alternatively, other models have been developed using artificial intelligence techniques such as neural networks. The aim of this paper is the development of a model to predict the compressive strength of concrete confined by polymers reinforced with aramid fibers using a multilayer perceptron neural network technique. However, a database of 212 experimental results obtained from the literature was used. The performance of the developed model was demonstrated by comparing the simulation results with those obtained by other theoretical models. In addition, a parametric study was conducted to verify the ability of the model to represent the effect of various parameters that control the compressive strength.

Detection of partial shading and short-circuit faults in a pv system using the artificial neural network multilayer perceptron technique

Photovoltaic (PV) systems play a crucial role in renewable energy production but face challenges due to environmental factors such as partial shading and short circuits, which reduce efficiency and reliability. Continuous monitoring and early fault detection are essential to mitigate these issues. In this work, we propose a fault detection method that focuses on identifying partial shading and short-circuit faults using an artificial neural network (ANN), specifically a Multi-Layer Perceptron (MLP). The MLP model is trained to classify these faults under various environmental scenarios, including situations where both faults occur simultaneously. The methodology involves simulating different fault scenarios using MATLAB/Simulink and training the MLP on input parameters such as voltage, current, and power output from the PV system. Results indicate that the proposed approach achieves high fault detection accuracy, minimizing classification errors and ensuring reliable identification of system failures. This research highlights the advantages of integrating ANN-based fault detection methods into PV system monitoring frameworks, enabling real-time diagnostics and proactive maintenance. By improving fault detection accuracy, the proposed method contributes to the operational efficiency, safety, and longevity of PV installations. This approach can be extended to large-scale PV systems, addressing the growing demand for reliable renewable energy solutions globally. The findings demonstrate the potential of ANN-based methods to enhance fault diagnostics, providing a scalable solution for modern PV systems and supporting the global transition to sustainable energy.

Best Practices for Database Security in the Age of AI

Database security has seen a dramatic change as a result of artificial intelligence's incorporation into contemporary technology, bringing with it previously unheard-of opportunities as well as obstacles. This thorough article looks at how businesses can use AI capabilities to safeguard sensitive data assets while fortifying their database security postures. With an emphasis on financial institutions and healthcare organizations, it looks at the changing threat landscape, crucial security measures, and practical implementation tactics across a range of sectors. The article further demonstrates the efficacy of threat detection systems, sophisticated encryption techniques, AI-powered security solutions, and thorough audit frameworks. It illustrates the vital significance of putting in place multi-layered security techniques that combine conventional safeguards with AI-enhanced protective measures through in-depth case studies and empirical analysis.

Anterior Skull Base Reconstruction in Multiportal Approaches: Insight into Vascularized Flap Techniques.

Background/Objectives: To evaluate the outcomes of anterior skull base (ASB) reconstruction using single versus double vascularized flap techniques following multiportal cranio-endoscopic approaches (CEA), based on a 12-year experience. Methods: A retrospective analysis was conducted on 46 patients who underwent ASB reconstruction after a CEA at our department between 2010 and 2022. Patients were divided into two groups: Group 1 received a pericranial flap (PF) reinforced with a fascia graft, while Group 2 underwent multiple flap reconstruction with PF, fascia graft, and nasoseptal flap (NSF). The primary outcome measured was the incidence of cerebrospinal fluid (CSF) leakage and the impact of adjuvant radiotherapy (RT) on reconstruction. Results: Group 1 (86.9%) demonstrated no significant postoperative CSF leaks, showing that the PF, combined with multilayer techniques (including underlay sealing matrix and overlay fascia graft), effectively repaired ASB defects. Group 2 (13.1%), employing both PF and NSF, showed similar outcomes, with the dual flap approach particularly beneficial in cases of post-traumatic fistulas or when the nasal septum was spared by disease. No significant differences were observed in complications or flap necrosis, even in patients receiving adjuvant RT. Conclusions: The PF is a reliable and versatile option for ASB reconstruction, often sufficient as a single-flap technique. The addition of an NSF can be beneficial in specific cases, particularly in post-traumatic conditions or tumors with unilateral endonasal invasion. However, PF alone, when combined with a multilayer approach, minimizes the risk of CSF leakage and long-term flap necrosis, underscoring the importance of tailored surgical strategies for optimal outcomes.

Static pinning synchronization control of self-triggered coupling dynamical networks

In this paper, a new static pinning intermittent control based on resource awareness triggering is proposed. A multi-layer control technique is used to synchronize the coupled neural network. First, a hierarchical network structure including pinned and interaction layers is induced using each pinning strategy. Second, using the ideas of average aperiodic intermittent control (AIC) rate method and constructing an auxiliary function, a new lemma is proposed for the pinning intermittent synchronization of coupled networks, where the upper/lower bound restrictions on each control width for AIC are relaxed. Third, to obtain the desired synchronization behavior, a self-triggering mechanism (STM) is proposed to execute the AIC of the pinned and interaction layers. Moreover, the proposed STM is effective for the actuation of the static pinning impulsive control. The static pinning method modifies the single pinning and switching pinning impulsive control. Finally, the proposed results are applied to Chua’s circuits, oscillators and small-world networks. Experimental results show the performance of the proposed STM which reduces 34.58% the number of control updates compared to a periodically intermittent event-triggered scheme. Further, for large-scale coupled networks, the N-dimensional Laplacian matrix LV can be decomposed into sp×sp and N−sp×N−sp dimensions by hierarchical method, thus reducing the complexity of calculation.

Opportunities with Multi-Layer Weave Structures in Woven E-Textile Design

Most textiles in day-to-day use are products of weaving. The versatility of this manufacturing technique, which readily supports a multi-layered structure, inclusion of several yarn types, malleability and other valuable characteristics, has attracted attention from HCI researchers intrigued by its potential to expand the interaction capabilities of e-textiles. Research nonetheless has barely scratched the surface of the wealth of weaving techniques and woven structures available. Therefore, a design-research project anchored in practice investigated how touch-sensitive e-textiles’ capabilities might be enriched via advanced multi-layer weaving techniques. The research process, which drew inspiration from literature both on textile design and on woven e-textiles, produced 25 distinct e-textile samples. Results from evaluating the structural properties, electrical capabilities and overall utility of each point to numerous unexplored opportunities from woven multi-layer e-textiles. Even holding potential for entirely new forms of interaction, these represent promising starting points for in-depth investigation.

An investigation of past and future LULC using multilayer perceptron-Markov chain techniques: a case study of a Himalayan smart city (2005–2040)

An investigation of past and future LULC using multilayer perceptron-Markov chain techniques: a case study of a Himalayan smart city (2005–2040)

Anterior Skull Base Reconstruction Using a Vascularized Pericranial Flap: A Promising Alternative in Sinonasal Malignancies

Abstract Background As the scope of endoscopic techniques continues to evolve in the treatment of advanced sinonasal malignancies, the primary challenge is the reconstruction of the resulting anterior skull base dural defect. Objective This study aimed to assess the efficacy of vascularized pericranial flap reconstruction in addressing anterior skull base defects in sinonasal malignancies, particularly when alternative reconstructive methods, such as nasoseptal flaps, are not viable. Methods We conducted a retrospective review of nine patients who underwent endoscopic resection of sinonasal malignancy followed by vascularized pericranial flap. Our analysis aimed to evaluate the surgical methods utilized, identify any complications that occurred, and assess the postoperative results of the patients. Results Excluding the singular instance of tension pneumocephalus that emerged during the immediate postoperative period, necessitating surgical intervention, our clinical experience was devoid of any complications, with a median follow-up duration of 18 months. It is worth noting that no cases of cerebrospinal fluid leaks or meningitis were reported. Moreover, the follow-up check endoscopy verified the successful integration of the flap and its efficacious coverage of the resection site. Conclusion This study underscores the benefits of using vascularized pericranial flaps as an alternative solution for anterior skull base reconstruction in sinonasal malignancies. The availability of the pericranial flap in the local region, along with its robust blood supply, and the positive outcomes observed in this preliminary series collectively indicate its potential as an integral component of multi-layered reconstruction techniques for addressing anterior skull base defects.

Multilayer networks in landscape ecology: a case study to assess changes in aquatic habitat connectivity for flying and non-flying benthic macroinvertebrates in a Danube floodplain

ContextIn efforts to mitigate anthropogenic impacts on floodplain biodiversity, restoration measures that enhance habitat connectivity have been applied. However, these approaches have either neglected the spatial position of water bodies or the dynamic nature of the floodplain ecosystem.ObjectivesThis study focuses on the novel application of the multilayer network framework to assess changes in the aquatic habitat connectivity in floodplains, showcasing its application in the context of aquatic passive dispersal (drift) of two indicator groups of benthic macroinvertebrates (Oligochaetes and Chironomids)MethodsOur case study is located in the Donau-Auen National Park in Austria and follows floodplain restoration measures (side-channel reconnection) applied in the mid-1990s. Multilayer networks were constructed to represent the conditions before, short-term, and long-term after restoration to quantify habitat connectivity across inundation frequencies. Our network analyses involved multilayer correlation, static and dynamic monolayer centralities (centrality profiles), and multilayer centrality assessments. We used a Partial Least Squares Regression analysis as a variable selection tool to identify which centrality measures better explained the variance in α\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\alpha$$\\end{document} diversity and Local Contributions to Beta Diversity (LCBD) of benthic macroinvertebrates.ResultsIn the short-term, our connectivity analysis indicated an increase in habitat connectivity. However, centrality profiles, multilayer correlation, and multilayer centrality techniques identified a long-term decrease in connectivity. Multilayer centralities had higher Variable Importance in the Projection scores (VIP) than their monolayer counterpart in explaining variations in α\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\alpha$$\\end{document} diversity and LCBD for strict aquatic dispersers. Meanwhile, for flying dispersers, monolayer centralities had the highest VIP scores for explaining α\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\alpha$$\\end{document} diversity.ConclusionsThis study underscores the relevance of integrating dynamic aspects of water-mediated transport beyond traditional pairwise distances. Although in this study we apply this tool by showcasing the aquatic passive dispersal mode, the application of this method can be extended to other dispersal modes and representative abilities for diverse groups of aquatic organisms. The expanding cross-disciplinary applications and open-source tool development for multilayer networks offer practical implications for planning and evaluating management measures.

High performance P300 spellers using GPT2 word prediction with cross-subject training

ABSTRACT Amyotrophic lateral sclerosis (ALS) severely impairs patients’ ability to communicate, often leading to a decline in their quality of life within a few years of diagnosis. The P300 speller brain–computer interface (BCI) offers an alternative communication method by interpreting a subject’s EEG response to flashing characters presented on a grid interface. This paper addresses the common speed limitations encountered in training efficient P300-based multi-subject classifiers by introducing innovative ‘across-subject’ classifiers. We leverage a combination of the second-generation Generative Pre-Trained Transformer (GPT2) and Dijkstra’s algorithm to optimize stimuli and suggest word completion choices based on subjects’ typing history. Additionally, we employ a multi-layered smoothing technique to accommodate out-of-vocabulary (OOV) words. Through extensive simulations employing random sampling of EEG data from multiple subjects, we demonstrate significant speed enhancements in typing passages containing rare and OOV words. These optimizations result in approximately 10 % improvement in character-level typing speed and up to 40 % improvement in multi-word prediction. We demonstrate that augmenting standard row/column highlighting techniques with layered word prediction yields close-to-optimal performance. Furthermore, we explore both ‘within-subject’ and ‘across-subject’ training techniques, showing that speed improvements are consistent across both approaches.

Design and Experimental Validation of an Adaptive Multi-Layer Neural Network Observer-Based Fast Terminal Sliding Mode Control for Quadrotor System

This study considers the numerical design and practical implementation of a new multi-layer neural network observer-based control design technique for unmanned aerial vehicles systems. Initially, an adaptive multi-layer neural network-based Luenberger observer is designed for state estimation by employing a modified back-propagation algorithm. The proposed observer’s adaptive nature aids in mitigating the impact of noise, disturbance, and parameter variations, which are usually not considered by conventional observers. Based on the observed states, a nonlinear dynamic inversion-based fast terminal sliding mode controller is designed to attain the desired attitude and position tracking control. This is done by employing a two-loop control structure. Numerical simulations are conducted to demonstrate the effectiveness of the proposed scheme in the presence of disturbance, parameter uncertainty, and noise. The numerical results are compared with current approaches, demonstrating the superiority of the proposed method. In order to assess the practical effectiveness of the proposed method, hardware-in-loop simulations are conducted by utilizing a Pixhawk 6X flight controller that interfaces with the mission planner software. Finally, experiments are conducted on a real F450 quadrotor in a secured laboratory environment, demonstrating stability and good tracking performance of the proposed MLNN observer-based SMC control scheme.

Prediction of CO2 uptake in bio-waste based porous carbons using model agnostic explainable artificial intelligence

This study introduces comprehensive research on the prediction of the carbon dioxide (CO2) uptake from the biomass-waste derived-porous carbons (BWDPCs), by using scientometrics and model agnostic multi-layered explainable artificial intelligence (XAI) techniques. It aims to identify the main characteristics, and trends that are specific to this domain, and to establish, compare and analyse the four different black box machine learning (ML) models for CO2 uptake prediction. For this study, through model evaluation parameters, and scatter plots, statistical analysis supports the fact that the Extreme Gradient Boosting (XGBoost) model is found to be the best performing model for CO2 uptake prediction with low errors and high coefficient of correlation for both training (MSE: 0.157, RMSE: 0.397, MAE: 0.294, MAPE: 0.112, R2: 0.931) and testing phases (MSE: 0.345, RMSE: 0.588, MAE: 0.461, MAPE: 0.121, R2: 0.860). Now, with the best performing black box ML model as XGBoost model, it serves as the basis for the multi-layered XAI analysis. Using multi-layered XAI techniques to interpret the black box ML model and covert it to a white box model, it makes clearer insights into the significant key features that affect the CO2 uptake both at the global and local level. The study demonstrates that using multi-layered XAI analysis helps in improving the trust of the predictive model and provides a way forward for the application of white box models in CO2 uptake.