RESUMO
Low-power and fast artificial neural network devices represent the direction in developing analogue neural networks. Here, an ultralow power consumption (0.8 fJ) and rapid (100 ns) La0.1Bi0.9FeO3/La0.7Sr0.3MnO3 ferroelectric tunnel junction artificial synapse has been developed to emulate the biological neural networks. The visual memory and forgetting functionalities have been emulated based on long-term potentiation and depression with good linearity. Moreover, with a single device, logical operations of "AND" and "OR" are implemented, and an artificial neural network was constructed with a recognition accuracy of 96%. Especially for noisy data sets, the recognition speed is faster after preprocessing by the device in the present work. This sets the stage for highly reliable and repeatable unsupervised learning.
RESUMO
This study presents a novel approach to design and optimize a sodium alginate-based hydrogel (SAH) for efficient adsorption of the model water pollutant methylene blue (MB) dye. Utilizing density functional theory (DFT) calculations, sodium alginate-g-poly (acrylamide-co-itaconic acid) was identified with the lowest adsorption energy (Eads) for MB dye among 14 different clusters. SAHs were prepared using selected monomers and sodium alginate combinations through graft co-polymerization, and swelling studies were conducted to optimize grafting conditions. Advanced characterization techniques, including FTIR, XRD, XPS, SEM, EDS, and TGA, were employed, and the process was optimized using statistical and machine learning tools. Screening tests demonstrated that Eads serves as an effective predicting indicator for adsorption capacity (qe) and MB removal efficiency (RRMB,%), with reasonable agreement between Eads and both responses under given conditions. Process modeling and optimization revealed that 5 mg of selected SAH achieves a maximum qe of 3244 mg g-1 at 84.4% RRMB under pH 8.05, 98.8 min, and MB concentration of 383.3 mg L-1, as identified by the desirability function approach. Moreover, SAH effectively eliminated various contaminants from aqueous solutions, including sulfasalazine (SFZ) and dibenzothiophene (DBT). MB adsorption onto selected SAH was exothermic, spontaneous, and followed the pseudo-first-order and Langmuir-Freundlich isotherm models. The remarkable ability of SAH to adsorb MB is attributed to its well-designed structure predicted through DFT and optimal operational conditions achieved by AI-based parametric optimization. By integrating DFT-based computations and machine-learning tools, this study contributes to the efficient design of adsorbent materials and optimization of adsorption processes, also showcasing the potential of SAH as an efficient adsorbent for the abatement of aqueous pollution.
Assuntos
Poluentes Ambientais , Poluentes Químicos da Água , Hidrogéis/química , Águas Residuárias , Corantes/química , Alginatos/química , Poluentes Químicos da Água/química , Água , Adsorção , Azul de Metileno/química , Cinética , Concentração de Íons de HidrogênioRESUMO
Lignites are widely available and cost-effective in many countries. Sustainable methods for their utilization drive innovation, potentially advancing environmental sustainability and resource efficiency. In the present study, Fe3O4 (â¼25.1 nm) supported on KOH-activated lignite (A-L) displayed 8 times higher phosphate removal than pristine A-L (67.6 mg/g vs. 8.5 mg/g at pH 5, 50 mg of absorbent in 25 mL of 1500 ppm [phosphate]), owing to its abundant Fe3O4 (10 wt% of Fe) nanoparticle content. The removal occurred within â¼2 h, following a pseudo-second-order kinetic model. Across pH levels ranging from 5.0 to 9.0, Fe3O4-A-L's phosphate removal occurs via both chemisorption and precipitation, as evident by kinetic, pH, and XPS analyses. The phosphate adsorption fits better with the Freundlich isotherm. The combined benefits of facile recovery, rapid phosphate uptake, straightforward regeneration, and attractive post-adsorption benefits (e.g., possibly use as a Fe, P-rich fertilizer) make magnetic Fe3O4-A-L a promising candidate for real-world applications. Artificial Neural Network (ANN) modeling indicates an excellent accuracy (R2 = 0.99) in predicting the amount of phosphate removed by Fe3O4-A-L. Sensitivity analysis revealed both temperature and initial concentration as the most influencing factors. Leveraging lignite in environmentally friendly applications not only addresses immediate challenges but also aligns with sustainability goals. The study clearly articulates the potential benefits of utilizing lignite for sustainable phosphate removal and recovery, offering avenues for mitigating environmental concerns while utilizing resources efficiently.
Assuntos
Redes Neurais de Computação , Fosfatos , Poluentes Químicos da Água , Fosfatos/química , Poluentes Químicos da Água/química , Poluentes Químicos da Água/análise , Adsorção , Carvão Mineral , Compostos Férricos/química , Cinética , Concentração de Íons de Hidrogênio , Purificação da Água/métodosRESUMO
Accurately predicting the characteristics of effluent, discharged from wastewater treatment plants (WWTPs) is crucial for reducing sampling requirements, labor, costs, and environmental pollution. Machine learning (ML) techniques can be effective in achieving this goal. To optimize ML-based models, various feature selection (FS) methods are employed. This study aims to investigate the impact of six FS methods (categorized as Wrapper, Filter, and Embedded methods) on the accuracy of three supervised ML algorithms in predicting total suspended solids (TSS) concentration in the effluent of a municipal wastewater treatment plant. Based on the features proposed by each FS method, five distinct scenarios were defined. Within each scenario, three ML algorithms, namely artificial neural network-multi layer perceptron (ANN-MLP), K-nearest neighbors (KNN), and adaptive boosting (AdaBoost) were applied. The features utilized for predicting TSS concentration in the WWTP effluent included BOD5, COD, TSS, TN, NH3 in the influent, and BOD5, COD, residual Cl2, NO3, TN, NH4 in the effluent. To construct the models, the dataset was randomly divided into training and testing subsets, and K-fold cross-validation was employed to control overfitting and underfitting. The evaluation metrics that are used are root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R2). The most efficient scenario was identified as Scenario IV, with the Sequential Backward Selection FS method. The features selected by this method were CODe, BOD5e, BOD5i, TNi. Furthermore, the ANN-MLP algorithm demonstrated the best performance, achieving the highest R2 value. This algorithm exhibited acceptable performance in both the training and testing subsets (R2 = 0.78 and R2 = 0.8, respectively).
Assuntos
Eliminação de Resíduos Líquidos , Purificação da Água , Eliminação de Resíduos Líquidos/métodos , Redes Neurais de Computação , Algoritmos , Aprendizado de Máquina , Purificação da Água/métodosRESUMO
Effective project planning and management in the global software development landscape relies on addressing major issues like cost estimation and effort allocation. Timely estimation of software development is a critical focus in software engineering research. With the industry increasingly relying on diverse teams worldwide, accurate estimation becomes vital. Software size serves as a common measure for costs and schedules, but advanced estimation methods consider various variables, such as project purpose, personnel expertise, time and efficiency constraints, and technology requirements. Estimating software costs involve significant financial and strategic commitments, making it crucial to address complexity and versatility related to cost drivers. To achieve enhanced accuracy and convergence, we employ the cuckoo algorithm in our proposed NFDLNN (Neuro Fuzzy Logic and Deep Learning Neural Networks) model. Through extensive validation with industrial project data, using Function Point Analysis as the algorithmic models, our NFA model demonstrates high accuracy in software cost approximation, outperforming existing methods insights of MRE of 3.33, BRE of 0.13, and PI of 74.48. Our research contributes to improved project planning and decision-making processes in global software development endeavours.
RESUMO
The burgeoning demand for durable and eco-friendly road infrastructure necessitates the exploration of innovative materials and methodologies. This study investigates the potential of Graphene Oxide (GO), a nano-material known for its exceptional dispersibility and mechanical reinforcement capabilities, to enhance the sustainability and durability of concrete pavements. Leveraging the synergy between advanced artificial intelligence techniques-Artificial Neural Networks (ANN), Genetic Algorithms (GA), and Particle Swarm Optimization (PSO)-it is aimed to delve into the intricate effects of Nano-GO on concrete's mechanical properties. The empirical analysis, underpinned by a comparative evaluation of ANN-GA and ANN-PSO models, reveals that the ANN-GA model excels with a minimal forecast error of 2.73%, underscoring its efficacy in capturing the nuanced interactions between GO and cementitious materials. An optimal concentration is identified through meticulous experimentation across varied Nano-GO dosages that amplify concrete's compressive, flexural, and tensile strengths without compromising workability. This optimal dosage enhances the initial strength significantly, and positions GO as a cornerstone for next-generation premium-grade pavement concretes. The findings advocate for the further exploration and eventual integration of GO in road construction projects, aiming to bolster ecological sustainability and propel the adoption of a circular economy in infrastructure development.
RESUMO
To ensure the structural integrity of concrete and prevent unanticipated fracturing, real-time monitoring of early-age concrete's strength development is essential, mainly through advanced techniques such as nano-enhanced sensors. The piezoelectric-based electro-mechanical impedance (EMI) method with nano-enhanced sensors is emerging as a practical solution for such monitoring requirements. This study presents a strength estimation method based on Non-Destructive Testing (NDT) Techniques and Long Short-Term Memory (LSTM) and artificial neural networks (ANNs) as hybrid (NDT-LSTMs-ANN), including several types of concrete strength-related agents. Input data includes water-to-cement rate, temperature, curing time, and maturity based on interior temperature, allowing experimentally monitoring the development of concrete strength from the early steps of hydration and casting to the last stages of hardening 28 days after the casting. The study investigated the impact of various factors on concrete strength development, utilizing a cutting-edge approach that combines traditional models with nano-enhanced piezoelectric sensors and NDT-LSTMs-ANN enhanced with nanotechnology. The results demonstrate that the hybrid provides highly accurate concrete strength estimation for construction safety and efficiency. Adopting the piezoelectric-based EMI technique with these advanced sensors offers a viable and effective monitoring solution, presenting a significant leap forward for the construction industry's structural health monitoring practices.
Assuntos
Materiais de Construção , Impedância Elétrica , Aprendizado de Máquina , Redes Neurais de Computação , Materiais de Construção/análise , Nanotecnologia/instrumentação , Nanotecnologia/métodos , Teste de Materiais/métodosRESUMO
This investigation assesses the embodied energy and carbon footprint in the manufacture of pavers using varying proportions of recycled Construction and Demolition Waste (CDW). Additionally, Thin Film Composite Polyamide fiber (TFC PA), extracted from end-of-life Reverse Osmosis (RO) membranes, is introduced as an additive to enhance the concrete's strength. Machine learning techniques, namely Artificial Neural Network (ANN), Support Vector Regression (SVR), and Response Surface Methodology (RSM), are employed to predict the mechanical properties of pavers. The study focuses on examining the energy required and embodied carbon in various mix proportions, as well as the mechanical properties-specifically compressive strength and split tensile strength of concrete with different CDW and TFC PA proportions. Findings reveal that the optimal percentage of TFC PA is 3 % for all CDW replacement proportions, resulting in low carbon content both in terms of energy and embodiment and in mechanical behavior. The implementation of ANN and SVR is conducted in MATLAB, while a Design Expert is employed to generate the experimental design for RSM. The RSM regression model demonstrates a robust correlation between variables and observed outcomes, with optimal p-values, R2 values, and f-values. The ANN model successfully captures the variability in the data. Additionally, the findings indicate a consistent superiority of the Support Vector Regression (SVR) model over both Artificial Neural Network (ANN) and Response Surface Model (RSM) models when considering diverse performance metrics such as residuals and correlation coefficients.
Assuntos
Carbono , Materiais de Construção , Resíduos Industriais/análise , Reciclagem/métodos , FiltraçãoRESUMO
PURPOSE: To build an Mult-Task Learning (MTL) based Artificial Intelligence(AI) model that can simultaneously predict clinical stage, histology, grade and LNM for cervical cancer before surgery. METHODS: This retrospective and prospective cohort study was conducted from January 2001 to March 2014 for the training set and from January 2018 to November 2021 for the validation set at Beijing Chaoyang Hospital, Capital Medical University. Preoperative clinical information of cervical cancer patients was used. An Artificial Neural Network (ANN) algorithm was used to build the MTL-based AI model. Accuracy and weighted F1 scores were calculated as evaluation indicators. The performance of the MTL model was compared with Single-Task Learning (STL) models. Additionally, a Turing test was performed by 20 gynecologists and compared with this AI model. RESULTS: A total of 223 cervical cancer cases were retrospectively enrolled into the training set, and 58 cases were prospectively collected as independent validation set. The accuracy of this cervical cancer AI model constructed with ANN algorithm in predicting stage, histology, grade and LNM were 75%, 95%, 86% and 76%, respectively. And the corresponding weighted F1 score were 70%, 94%, 86%, and 76%, respectively. The average time consumption of AI simultaneously predicting stage, histology, grade and LNM for cervical cancer was 0.01s (95%CI: 0.01-0.01) per 20 patients. The mean time consumption doctor and doctor with AI were 581.1s (95%CI: 300.0-900.0) per 20 patients and 534.8s (95%CI: 255.0-720.0) per 20 patients, respectively. Except for LNM, both the accuracy and F-score of the AI model were significantly better than STL AI, doctors and AI-assisted doctors in predicting stage, grade and histology. (P < 0.05) The time consumption of AI was significantly less than that of doctors' prediction and AI-assisted doctors' results. (P < 0.05 CONCLUSION: A multi-task learning AI model can simultaneously predict stage, histology, grade, and LNM for cervical cancer preoperatively with minimal time consumption. To improve the conditions and use of the beneficiaries, the model should be integrated into routine clinical workflows, offering a decision-support tool for gynecologists. Future studies should focus on refining the model for broader clinical applications, increasing the diversity of the training datasets, and enhancing its adaptability to various clinical settings. Additionally, continuous feedback from clinical practice should be incorporated to ensure the model's accuracy and reliability, ultimately improving personalized patient care and treatment outcomes.
Assuntos
Inteligência Artificial , Neoplasias do Colo do Útero , Humanos , Feminino , Neoplasias do Colo do Útero/cirurgia , Neoplasias do Colo do Útero/patologia , Estudos Retrospectivos , Estudos Prospectivos , Pessoa de Meia-Idade , Adulto , Estadiamento de Neoplasias/métodos , Gradação de Tumores/métodos , Redes Neurais de Computação , Algoritmos , Idoso , Metástase Linfática , Estudos de CoortesRESUMO
New process developments linked to Power to X (energy storage or energy conversion to another form of energy) require tools to perform process monitoring. The main gases involved in these types of processes are H2, CO, CH4, and CO2. Because of the non-selectivity of the sensors, a multi-sensor matrix has been built in this work based on commercial sensors having very different transduction principles, and, therefore, providing richer information. To treat the data provided by the sensor array and extract gas mixture composition (nature and concentration), linear (Multi Linear Regression-Ordinary Least Square "MLR-OLS" and Multi Linear Regression-Partial Least Square "MLR-PLS") and non-linear (Artificial Neural Network "ANN") models have been built. The MLR-OLS model was disqualified during the training phase since it did not show good results even in the training phase, which could not lead to effective predictions during the validation phase. Then, the performances of MLR-PLS and ANN were evaluated with validation data. Good concentration predictions were obtained in both cases for all the involved analytes. However, in the case of methane, better prediction performances were obtained with ANN, which is consistent with the fact that the MOX sensor's response to CH4 is logarithmic, whereas only linear sensor responses were obtained for the other analytes. Finally, prediction tests performed on one-year aged sensor platforms revealed that PLS model predictions on aged platforms mainly suffered from concentration offsets and that ANN predictions mainly suffered from a drop of sensitivity.
RESUMO
Organizations managing high-performance computing systems face a multitude of challenges, including overarching concerns such as overall energy consumption, microprocessor clock frequency limitations, and the escalating costs associated with chip production. Evidently, processor speeds have plateaued over the last decade, persisting within the range of 2 GHz to 5 GHz. Scholars assert that brain-inspired computing holds substantial promise for mitigating these challenges. The spiking neural network (SNN) particularly stands out for its commendable power efficiency when juxtaposed with conventional design paradigms. Nevertheless, our scrutiny has brought to light several pivotal challenges impeding the seamless implementation of large-scale neural networks (NNs) on silicon. These challenges encompass the absence of automated tools, the need for multifaceted domain expertise, and the inadequacy of existing algorithms to efficiently partition and place extensive SNN computations onto hardware infrastructure. In this paper, we posit the development of an automated tool flow capable of transmuting any NN into an SNN. This undertaking involves the creation of a novel graph-partitioning algorithm designed to strategically place SNNs on a network-on-chip (NoC), thereby paving the way for future energy-efficient and high-performance computing paradigms. The presented methodology showcases its effectiveness by successfully transforming ANN architectures into SNNs with a marginal average error penalty of merely 2.65%. The proposed graph-partitioning algorithm enables a 14.22% decrease in inter-synaptic communication and an 87.58% reduction in intra-synaptic communication, on average, underscoring the effectiveness of the proposed algorithm in optimizing NN communication pathways. Compared to a baseline graph-partitioning algorithm, the proposed approach exhibits an average decrease of 79.74% in latency and a 14.67% reduction in energy consumption. Using existing NoC tools, the energy-latency product of SNN architectures is, on average, 82.71% lower than that of the baseline architectures.
RESUMO
To address the uncertainty of optimal vibratory frequency fov of high-speed railway graded gravel (HRGG) and achieve high-precision prediction of the fov, the following research was conducted. Firstly, commencing with vibratory compaction experiments and the hammering modal analysis method, the resonance frequency f0 of HRGG fillers, varying in compactness K, was initially determined. The correlation between f0 and fov was revealed through vibratory compaction experiments conducted at different vibratory frequencies. This correlation was established based on the compaction physical-mechanical properties of HRGG fillers, encompassing maximum dry density ρdmax, stiffness Krd, and bearing capacity coefficient K20. Secondly, the gray relational analysis algorithm was used to determine the key feature influencing the fov based on the quantified relationship between the filler feature and fov. Finally, the key features influencing the fov were used as input parameters to establish the artificial neural network prediction model (ANN-PM) for fov. The predictive performance of ANN-PM was evaluated from the ablation study, prediction accuracy, and prediction error. The results showed that the ρdmax, Krd, and K20 all obtained optimal states when fov was set as f0 for different gradation HRGG fillers. Furthermore, it was found that the key features influencing the fov were determined to be the maximum particle diameter dmax, gradation parameters b and m, flat and elongated particles in coarse aggregate Qe, and the Los Angeles abrasion of coarse aggregate LAA. Among them, the influence of dmax on the ANN-PM predictive performance was the most significant. On the training and testing sets, the goodness-of-fit R2 of ANN-PM all exceeded 0.95, and the prediction errors were small, which indicated that the accuracy of ANN-PM predictions was relatively high. In addition, it was clear that the ANN-PM exhibited excellent robust performance. The research results provide a novel method for determining the fov of subgrade fillers and provide theoretical guidance for the intelligent construction of high-speed railway subgrades.
RESUMO
Monitoring heart conditions through electrocardiography (ECG) has been the cornerstone of identifying cardiac irregularities. Cardiologists often rely on a detailed analysis of ECG recordings to pinpoint deviations that are indicative of heart anomalies. This traditional method, while effective, demands significant expertise and is susceptible to inaccuracies due to its manual nature. In the realm of computational analysis, Artificial Neural Networks (ANNs) have gained prominence across various domains, which can be attributed to their superior analytical capabilities. Conversely, Spiking Neural Networks (SNNs), which mimic the neural activity of the brain more closely through impulse-based processing, have not seen widespread adoption. The challenge lies primarily in the complexity of their training methodologies. Despite this, SNNs offer a promising avenue for energy-efficient computational models capable of displaying a high-level performance. This paper introduces an innovative approach employing SNNs augmented with an attention mechanism to enhance feature recognition in ECG signals. By leveraging the inherent efficiency of SNNs, coupled with the precision of attention modules, this model aims to refine the analysis of cardiac signals. The novel aspect of our methodology involves adapting the learned parameters from ANNs to SNNs using leaky integrate-and-fire (LIF) neurons. This transfer learning strategy not only capitalizes on the strengths of both neural network models but also addresses the training challenges associated with SNNs. The proposed method is evaluated through extensive experiments on two publicly available benchmark ECG datasets. The results show that our model achieves an overall accuracy of 93.8% on the MIT-BIH Arrhythmia dataset and 85.8% on the 2017 PhysioNet Challenge dataset. This advancement underscores the potential of SNNs in the field of medical diagnostics, offering a path towards more accurate, efficient, and less resource-intensive analyses of heart diseases.
Assuntos
Eletrocardiografia , Redes Neurais de Computação , Neurônios , Eletrocardiografia/métodos , Humanos , Neurônios/fisiologia , Algoritmos , Processamento de Sinais Assistido por ComputadorRESUMO
This study aims to illustrate the design, fabrication, and optimisation of an ultrasonic welding (UW) machine to join copper wires with non-woven PVC textiles as smart textiles. The study explicitly evaluates UW parameters' impact on heat generation, joint strength, and electrical properties, with a comprehensive understanding of the process dynamics and developing a predictive model applicable to smart textiles. The methodological approach involved designing and manufacturing an ultrasonic piezoelectric transducer using ABAQUS finite element analyses (FEA) software and constructing a UW machine for the current purpose. The full factorial design (FFD) approach was employed in experiments to systematically assess the influence of welding time, welding pressure, and copper wire diameter on the produced joints. Experimental data were meticulously collected, and a backpropagation neural network (BPNN) model was constructed based on the analysis of these results. The results of the experimental investigation provided valuable insights into the UW process, elucidating the intricate relationship between welding parameters and heat generation, joint strength, and post-welding electrical properties of the copper wires. This dataset served as the basis for developing a neural network model, showcasing a high level of accuracy in predicting welding outcomes compared to the FFD model. The neural network model provides a valuable tool for controlling and optimising the UW process in the realm of smart textile production.
RESUMO
Bridges are critical infrastructures that support our economic activities and daily lives. Aging bridges have been a major issue for decades, prompting researchers to improve resilience and performance through structural health monitoring. While most research focuses on superstructure damage, the majority of bridge failures are associated with support or joint damages, indicating the importance of bridge support. Indeed, bridge support affects the performance of both the substructure and superstructure by maintaining the load path and allowing certain movements to mitigate thermal and other stresses. The support deterioration leads to a change in fixity in the superstructure, compromising the bridge's integrity and safety. Hence, a reliable method to determine support fixity level is essential to detecting bearing health and enhancing the accuracy of the bridge health monitoring system. However, such research is lacking because of its complexity. In this study, we developed a support fixity quantification method based on thermal responses using an Artificial Neural Network (ANN) model. A finite element (FE) model of a representative highway bridge is used to derive thermal displacement data under different bearing stiffnesses, superstructure damage, and thermal loading. The thermal displacement behavior of the bridge under different support fixity conditions is presented, and the model is trained on the simulated response. The performance of the developed FE model and ANN was validated with field monitoring data collected from two in-service bridges in Connecticut using a real-time Wireless Sensor Network (WSN). Finally, the support stiffnesses of both bridges were predicted using the ANN model for validation.
RESUMO
Artificial neural networks (ANNs) are nowadays applied as the most efficient methods in the majority of machine learning approaches, including data-driven modeling for assessment of the toxicity of chemicals. We developed a combined neural network methodology that can be used in the scope of new approach methodologies (NAMs) assessing chemical or drug toxicity. Here, we present QSAR models for predicting the physical and biochemical properties of molecules of three different datasets: aqueous solubility, acute fish toxicity toward fat head minnow, and bio-concentration factors. A novel neural network modeling method is developed by combining two neural network algorithms, namely, the counter-propagation modeling strategy (CP-ANN) with the back-propagation-of-errors algorithm (BPE-ANN). The advantage is a short training time, robustness, and good interpretability through the initial CP-ANN part, while the extension with BPE-ANN improves the precision of predictions in the range between minimal and maximal property values of the training data, regardless of the number of neurons in both neural networks, either CP-ANN or BPE-ANN.
Assuntos
Algoritmos , Redes Neurais de Computação , Animais , Relação Quantitativa Estrutura-Atividade , Aprendizado de MáquinaRESUMO
Studying drug-target interactions (DTIs) is the foundational and crucial phase in drug discovery. Biochemical experiments, while being the most reliable method for determining drug-target affinity (DTA), are time-consuming and costly, making it challenging to meet the current demands for swift and efficient drug development. Consequently, computational DTA prediction methods have emerged as indispensable tools for this research. In this article, we propose a novel deep learning algorithm named GRA-DTA, for DTA prediction. Specifically, we introduce Bidirectional Gated Recurrent Unit (BiGRU) combined with a soft attention mechanism to learn target representations. We employ Graph Sample and Aggregate (GraphSAGE) to learn drug representation, especially to distinguish the different features of drug and target representations and their dimensional contributions. We merge drug and target representations by an attention neural network (ANN) to learn drug-target pair representations, which are fed into fully connected layers to yield predictive DTA. The experimental results showed that GRA-DTA achieved mean squared error of 0.142 and 0.225 and concordance index reached 0.897 and 0.890 on the benchmark datasets KIBA and Davis, respectively, surpassing the most state-of-the-art DTA prediction algorithms.
Assuntos
Algoritmos , Aprendizado Profundo , Redes Neurais de Computação , Descoberta de Drogas/métodos , Humanos , Preparações Farmacêuticas/químicaRESUMO
The current study focuses on analyzing the impacts of climate change and land use/land cover (LULC) changes on sediment yield in the Puthimari basin, an Eastern Himalayan sub-watershed of the Brahmaputra, using a hybrid SWAT-ANN model approach. The analysis was meticulously segmented into three distinct time spans: 2025-2049, 2050-2074, and 2075-2099. This innovative method integrates insights from multiple climate models under two Representative Concentration Pathways (RCP4.5 and RCP8.5), along with LULC projections generated through the Cellular Automata Markov model. By combining the strengths of the Soil and Water Assessment Tool (SWAT) and artificial neural network (ANN) techniques, the study aims to improve the accuracy of sediment yield simulations in response to changing environmental conditions. The non-linear autoregressive with external input (NARX) method was adopted for the ANN component of the hybrid model. The adoption of the hybrid SWAT-ANN approach appears to be particularly effective in improving the accuracy of sediment yield simulation compared to using the SWAT model alone, as evidenced by the higher coefficient of determination value of 0.74 for the hybrid model compared to 0.35 for the standalone SWAT model. In the context of the RCP4.5 scenario, during 2075-99, the study noted a 29.34% increase in sediment yield, accompanied by simultaneous rises of 42.74% in discharge and 27.43% in rainfall during the Indian monsoon season, spanning from June to September. In contrast, under the RCP8.5 scenario, for the same period, the increases in sediment yield, discharge, and rainfall for the monsoon season were determined to be 116.56%, 103.28%, and 64.72%, respectively. The present study's comprehensive analysis of the factors influencing sediment supply in the Puthimari River basin fills an important knowledge gap and provides valuable insights for designing proactive flood and erosion management strategies. The findings from this research are crucial for understanding the vulnerability of the Puthimari basin to climate and land use changes, and by incorporating these findings into policy and decision-making processes, stakeholders can work towards enhancing resilience and sustainability in the face of future hydrological and environmental challenges.
Assuntos
Mudança Climática , Sedimentos Geológicos , Redes Neurais de Computação , Monitoramento Ambiental/métodos , Modelos Teóricos , Solo/químicaRESUMO
The removal of turbidity from abattoir wastewater (AWW) by electrocoagulation (EC) was modeled and optimized using Artificial Intelligence (AI) algorithms. Artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), particle swarm optimization (PSO), and genetic algorithms (GA) were the AI tools employed. Five input variables were considered: pH, current intensity, electrolysis time, settling time, and temperature. The ANN model was evaluated using the Levenberg-Marquardt (trainlm) algorithm, while the ANFIS modeling was accomplished using the Sugeno-type FIS. The ANN and ANFIS models demonstrated linear adequacy with the experimental data, with an R2 value of 0.9993 in both cases. The corresponding statistical error indices were RMSE (ANN = 5.65685E-05; ANFIS = 2.82843E-05), SSE (ANN = 1.60E-07; ANFIS = 3.4E-08), and MSE (ANN = 3.2E-09; ANFIS = 8E-10). The error indices revealed that the ANFIS model had the least performance error and is considered the most reliable of the two. The process optimization performed with GA and PSO considered turbidity removal efficiency, energy requirement, and electrode material loss. An optimal turbidity removal efficiency of 99.39 % was predicted at pH (3.1), current intensity (2 A), electrolysis time (20 min), settling time (50 min), and operating temperature (50 °C). This represents a potential for the delivery of cleaner water without the use of chemicals. The estimated power consumption and the theoretical mass of the aluminium electrode dissolved at the optimum condition were 293.33 kW h/m3 and 0.2237 g, respectively. The work successfully affirmed the effectiveness of the EC process in the removal of finely divided suspended particles from AWW and demonstrated the suitability of the AI algorithms in the modeling and optimization of the process.
Assuntos
Alumínio , Inteligência Artificial , Águas Residuárias , Lógica Fuzzy , Matadouros , Algoritmos , Eletrocoagulação , EletrodosRESUMO
This study assessed the accuracy of various methods for estimating lake evaporation in arid, high-wind environments, leveraging water temperature data from Landsat 8. The evaluation involved four estimation techniques: the FAO 56 radiation-based equation, the Schendel temperature-based equation, the Brockamp & Wenner mass transfer-based equation, and the VUV regression-based equation. The study focused on the Chah Nimeh Reservoirs (CNRs) in the arid region of Iran due to its distinctive wind patterns and dry climate. Our analysis revealed that the Split-window algorithm was the most precise for satellite-based water surface temperature measurement, with an R2 value of 0.86 and an RMSE of 1.61 °C. Among evaporation estimation methods, the FAO 56 stood out, demonstrating an R2 value of 0.76 and an RMSE of 4.36 mm/day in comparison to pan evaporation measurements. A subsequent sensitivity analysis using an artificial neural network (ANN) identified net radiation as the predominant factor influencing lake evaporation, especially during both wind and no-wind conditions. This research underscores the importance of incorporating net radiation, water surface temperature, and wind speed parameters in evaporation evaluations, providing pivotal insights for effective water management in arid, windy regions.