Search results for: classifiers accuracy

Authors: Nanine Fouche

Abstract:

The Cape Flats is a low-lying sand-covered expanse of approximately 460 square kilometres, situated to the southeast of the central business district of Cape Town in the Western Cape of South Africa. The aeolian sands masking this area are often loose and compressible in the upper 1m to 1.5m of the surface, and there is a general exceedance of the maximum allowable settlement in these sands. The settlement of shallow foundations on Cape Flats sands is commonly predicted using the results of in-situ tests such as the SPT or DPSH due to the difficulty of retrieving undisturbed samples for laboratory testing. Varying degrees of accuracy and reliability are associated with these methods. More recently, shear wave velocity (Vs) profiles obtained from seismic testing, such as continuous surface wave tests (CSW), are being used for settlement prediction. Such predictions have the advantage of considering non-linear stress-strain behaviour of soil and the degradation of stiffness with increasing strain. CSW tests are rarely executed in the Cape Flats, whereas SPT’s are commonly performed. For this reason, and to facilitate better settlement predictions in Cape Flats sand, equations representing shear wave velocity (Vs) as a function of SPT blow count (N60) and vertical effective stress (v’) were generated by statistical regression of site investigation data. To reveal the most appropriate method of overburden correction, analyses were performed with a separate overburden term (Pa/σ’v) as well as using stress corrected shear wave velocity and SPT blow counts (correcting Vs. and N60 to Vs1and (N1)60respectively). Shear wave velocity profiles and SPT blow count data from three sites masked by Cape Flats sands were utilised to generate 80 Vs-SPT N data pairs for analysis. Investigated terrains included sites in the suburbs of Athlone, Muizenburg, and Atlantis, all underlain by windblown deposits comprising fine and medium sand with varying fines contents. Elastic settlement analysis was also undertaken for the Cape Flats sands, using a non-linear stepwise method based on small-strain stiffness estimates, which was obtained from the best Vs-N60 model and compared to settlement estimates using the general elastic solution with stiffness profiles determined using Stroud’s (1989) and Webb’s (1969) SPT N60-E transformation models. Stroud’s method considers strain level indirectly whereasWebb’smethod does not take account of the variation in elastic modulus with strain. The expression of Vs. in terms of N60 and Pa/σv’ derived from the Atlantis data set revealed the best fit with R2 = 0.83 and a standard error of 83.5m/s. Less accurate Vs-SPT N relations associated with the combined data set is presumably the result of inversion routines used in the analysis of the CSW results showcasing significant variation in relative density and stiffness with depth. The regression analyses revealed that the inclusion of a separate overburden term in the regression of Vs and N60, produces improved fits, as opposed to the stress corrected equations in which the R2 of the regression is notably lower. It is the correction of Vs and N60 to Vs1 and (N1)60 with empirical constants ‘n’ and ‘m’ prior to regression, that introduces bias with respect to overburden pressure. When comparing settlement prediction methods, both Stroud’s method (considering strain level indirectly) and the small strain stiffness method predict higher stiffnesses for medium dense and dense profiles than Webb’s method, which takes no account of strain level in the determination of soil stiffness. Webb’s method appears to be suitable for loose sands only. The Versak software appears to underestimate differences in settlement between square and strip footings of similar width. In conclusion, settlement analysis using small-strain stiffness data from the proposed Vs-N60 model for Cape Flats sands provides a way to take account of the non-linear stress-strain behaviour of the sands when calculating settlement.

Keywords: sands, settlement prediction, continuous surface wave test, small-strain stiffness, shear wave velocity, penetration resistance

Procedia PDF Downloads 177

Authors: Faruk Ozdemir, Roy Kalawsky, Peter Hubbard

Abstract:

Accurate estimation of RUL provides a basis for effective predictive maintenance, reducing unexpected downtime for industrial equipment. However, while models such as the Random Forest have effective predictive capabilities, they are the so-called ‘black box’ models, where interpretability is at a threshold to make critical diagnostic decisions involved in industries related to aviation. The purpose of this work is to present a prognostic framework that embeds Explainable Artificial Intelligence (XAI) techniques in order to provide essential transparency in Machine Learning methods' decision-making mechanisms based on sensor data, with the objective of procuring actionable insights for the aviation industry. Sensor readings have been gathered from critical equipment such as turbofan jet engine and landing gear, and the prediction of the RUL is done by a Random Forest model. It involves steps such as data gathering, feature engineering, model training, and evaluation. These critical components’ datasets are independently trained and evaluated by the models. While suitable predictions are served, their performance metrics are reasonably good; such complex models, however obscure reasoning for the predictions made by them and may even undermine the confidence of the decision-maker or the maintenance teams. This is followed by global explanations using SHAP and local explanations using LIME in the second phase to bridge the gap in reliability within industrial contexts. These tools analyze model decisions, highlighting feature importance and explaining how each input variable affects the output. This dual approach offers a general comprehension of the overall model behavior and detailed insight into specific predictions. The proposed framework, in its third component, incorporates the techniques of causal analysis in the form of Granger causality tests in order to move beyond correlation toward causation. This will not only allow the model to predict failures but also present reasons, from the key sensor features linked to possible failure mechanisms to relevant personnel. The causality between sensor behaviors and equipment failures creates much value for maintenance teams due to better root cause identification and effective preventive measures. This step contributes to the system being more explainable. Surrogate Several simple models, including Decision Trees and Linear Models, can be used in yet another stage to approximately represent the complex Random Forest model. These simpler models act as backups, replicating important jobs of the original model's behavior. If the feature explanations obtained from the surrogate model are cross-validated with the primary model, the insights derived would be more reliable and provide an intuitive sense of how the input variables affect the predictions. We then create an iterative explainable feedback loop, where the knowledge learned from the explainability methods feeds back into the training of the models. This feeds into a cycle of continuous improvement both in model accuracy and interpretability over time. By systematically integrating new findings, the model is expected to adapt to changed conditions and further develop its prognosis capability. These components are then presented to the decision-makers through the development of a fully transparent condition monitoring and alert system. The system provides a holistic tool for maintenance operations by leveraging RUL predictions, feature importance scores, persistent sensor threshold values, and autonomous alert mechanisms. Since the system will provide explanations for the predictions given, along with active alerts, the maintenance personnel can make informed decisions on their end regarding correct interventions to extend the life of the critical machinery.

Keywords: predictive maintenance, explainable artificial intelligence, prognostic, RUL, machine learning, turbofan engines, C-MAPSS dataset

Procedia PDF Downloads 10

Authors: Rowan Moore, Kai Scheffler, Eugen Damoc, Jennifer Sutton, Aaron Bailey, Stephane Houel, Simon Cubbon, Jonathan Josephs

Abstract:

Purpose: MS analysis of monoclonal antibodies (mAbs) at the protein and peptide levels is critical during development and production of biopharmaceuticals. The compositions of current generation therapeutic proteins are often complex due to various modifications which may affect efficacy. Intact proteins analyzed by MS are detected in higher charge states that also provide more complexity in mass spectra. Protein analysis in native or native-like conditions with zero or minimal organic solvent and neutral or weakly acidic pH decreases charge state value resulting in mAb detection at higher m/z ranges with more spatial resolution. Methods: Three commercially available mAbs were used for all experiments. Intact proteins were desalted online using size exclusion chromatography (SEC) or reversed phase chromatography coupled on-line with a mass spectrometer. For streamlined use of the LC- MS platform we used a single SEC column and alternately selected specific mobile phases to perform separations in either denaturing or native-like conditions: buffer A (20 % ACN, 0.1 % FA) with Buffer B (100 mM ammonium acetate). For peptide analysis mAbs were proteolytically digested with and without prior reduction and alkylation. The mass spectrometer used for all experiments was a commercially available Thermo Scientific™ hybrid Quadrupole-Orbitrap™ mass spectrometer, equipped with the new BioPharma option which includes a new High Mass Range (HMR) mode that allows for improved high mass transmission and mass detection up to 8000 m/z. Results: We have analyzed the profiles of three mAbs under reducing and native conditions by direct infusion with offline desalting and with on-line desalting via size exclusion and reversed phase type columns. The presence of high salt under denaturing conditions was found to influence the observed charge state envelope and impact mass accuracy after spectral deconvolution. The significantly lower charge states observed under native conditions improves the spatial resolution of protein signals and has significant benefits for the analysis of antibody mixtures, e.g. lysine variants, degradants or sequence variants. This type of analysis requires the detection of masses beyond the standard mass range ranging up to 6000 m/z requiring the extended capabilities available in the new HMR mode. We have compared each antibody sample that was analyzed individually with mixtures in various relative concentrations. For this type of analysis, we observed that apparent native structures persist and ESI is benefited by the addition of low amounts of acetonitrile and formic acid in combination with the ammonium acetate-buffered mobile phase. For analyses on the peptide level we analyzed reduced/alkylated, and non-reduced proteolytic digests of the individual antibodies separated via reversed phase chromatography aiming to retrieve as much information as possible regarding sequence coverage, disulfide bridges, post-translational modifications such as various glycans, sequence variants, and their relative quantification. All data acquired were submitted to a single software package for analysis aiming to obtain a complete picture of the molecules analyzed. Here we demonstrate the capabilities of the mass spectrometer to fully characterize homogeneous and heterogeneous therapeutic proteins on one single platform. Conclusion: Full characterization of heterogeneous intact protein mixtures by improved mass separation on a quadrupole-Orbitrap™ mass spectrometer with extended capabilities has been demonstrated.

Keywords: disulfide bond analysis, intact analysis, native analysis, mass spectrometry, monoclonal antibodies, peptide mapping, post-translational modifications, sequence variants, size exclusion chromatography, therapeutic protein analysis, UHPLC

Procedia PDF Downloads 365

Authors: Atish Bagchi, Siva Chandrasekaran

Abstract:

Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.

Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning

Procedia PDF Downloads 151

Authors: M. Moreno, M. Alique, D. Otero, C. Delgado, P. Lacharmoise, L. Gracia, L. Pires, A. Moya

Abstract:

Marine environments are increasingly threatened by heavy metal contamination, including mercury (Hg), lead (Pb), and cadmium (Cd), posing significant risks to ecosystems and human health. Traditional monitoring techniques often fail to provide the spatial and temporal resolution needed for real-time detection of these contaminants, especially in remote or harsh environments. SEAWIZARD addresses these challenges by leveraging the flexibility, adaptability, and cost-effectiveness of printed electronics, with the integration of microfluidics to develop a compact, portable, and reusable sensor platform designed specifically for real-time monitoring of heavy metal ions in seawater. The SEAWIZARD sensor is a multiparametric Lab-on-Chip (LoC) device, a miniaturized system that integrates several laboratory functions into a single chip, drastically reducing sample volumes and improving adaptability. This platform integrates three printed graphene electrodes for the simultaneous detection of Hg, Cd and Pb via square wave voltammetry. These electrodes share the reference and the counter electrodes to improve space efficiency. Additionally, it integrates printed pH and temperature sensors to correct environmental interferences that may impact the accuracy of metal detection. The pH sensor is based on a carbon electrode with iridium oxide electrodeposited while the temperature sensor is graphene based. A protective dielectric layer is printed on top of the sensor to safeguard it in harsh marine conditions. The use of flexible polyethylene terephthalate (PET) as the substrate enables the sensor to conform to various surfaces and operate in challenging environments. One of the key innovations of SEAWIZARD is its integrated microfluidic layer, fabricated from cyclic olefin copolymer (COC). This microfluidic component allows a controlled flow of seawater over the sensing area, allowing for significant improved detection limits compared to direct water sampling. The system’s dual-channel design separates the detection of heavy metals from the measurement of pH and temperature, ensuring that each parameter is measured under optimal conditions. In addition, the temperature sensor is finely tuned with a serpentine-shaped microfluidic channel to ensure precise thermal measurements. SEAWIZARD also incorporates custom electronics that allow for wireless data transmission via Bluetooth, facilitating rapid data collection and user interface integration. Embedded artificial intelligence further enhances the platform by providing an automated alarm system, capable of detecting predefined metal concentration thresholds and issuing warnings when limits are exceeded. This predictive feature enables early warnings of potential environmental disasters, such as industrial spills or toxic levels of heavy metal pollutants, making SEAWIZARD not just a detection tool, but a comprehensive monitoring and early intervention system. In conclusion, SEAWIZARD represents a significant advancement in printed electronics applied to environmental sensing. By combining flexible, low-cost materials with advanced microfluidics, custom electronics, and AI-driven intelligence, SEAWIZARD offers a highly adaptable and scalable solution for real-time, high-resolution monitoring of heavy metals in marine environments. Its compact and portable design makes it an accessible, user-friendly tool with the potential to transform water quality monitoring practices and provide critical data to protect marine ecosystems from contamination-related risks.

Keywords: lab-on-chip, printed electronics, real-time monitoring, microfluidics, heavy metal contamination

Procedia PDF Downloads 39

Authors: Katie M. Clark, Adriana A. Tienda, Krista C. Paffenroth, Lindsey N. Brigante, Daniel C. Colvin, Jose Maldonado, Erin S. Calipari, Fiona E. Harrison

Abstract:

Manganese (Mn) is an essential trace element required for human health and is important in antioxidant defenses, as well as in the development and function of dopaminergic neurons. However, chronic low-level Mn exposure, such as through contaminated drinking water, poses risks that may contribute to neurodevelopmental and neurodegenerative conditions, including attention deficit hyperactivity disorder (ADHD). Pharmacological inhibition of the dopamine transporter (DAT) blocks reuptake, elevates synaptic dopamine, and alleviates ADHD symptoms. This study aimed to determine whether Mn exposure in juvenile mice modifies their response to DAT blockers, amphetamine, and methylphenidate and utilize neuroimaging methods to visualize and quantify Mn distribution across dopaminergic brain regions. Male and female heterozygous DATᵀ³⁵⁶ᴹ and wild-type littermates were randomly assigned to receive control (2.5% Stevia) or high Manganese (2.5 mg/ml Mn + 2.5% Stevia) via water ad libitum from weaning (21-28 days) for 4-5 weeks. Mice underwent repeated testing in locomotor activity chambers for three consecutive days (60 mins.) to ensure that they were fully habituated to the environments. On the fourth day, a 3-hour activity session was conducted following treatment with amphetamine (3 mg/kg) or methylphenidate (5 mg/kg). The second drug was administered in a second 3-hour activity session following a 1-week washout period. Following the washout, the mice were given one last injection of amphetamine and euthanized one hour later. Using the ex-vivo brains, magnetic resonance relaxometry (MRR) was performed on a 7Telsa imaging system to map T1- and T2-weighted (T1W, T2W) relaxation times. Mn inherent paramagnetic properties shorten both T1W and T2W times, which enhances the signal intensity and contrast, enabling effective visualization of Mn accumulation in the entire brain. A subset of mice was treated with amphetamine 1 hour before euthanasia. SmartSPIM light sheet microscopy with cleared whole brains and cFos and tyrosine hydroxylase (TH) labeling enabled an unbiased automated counting and densitometric analysis of TH and cFos positive cells. Immunohistochemistry was conducted to measure synaptic protein markers and quantify changes in neurotransmitter regulation. Mn exposure elevated Mn brain levels and potentiated stimulant effects in males. The globus pallidus, substantia nigra, thalamus, and striatum exhibited more pronounced T1W shortening, indicating regional susceptibility to Mn accumulation (p<0.0001, 2-Way ANOVA). In the cleared whole brains, initial analyses suggest that TH and c-Fos co-staining mirrors behavioral data with decreased co-staining in DATT356M+/- mice. Ongoing studies will identify the molecular basis of the effect of Mn, including changes to DAergic metabolism and transport and post-translational modification to the DAT. These findings demonstrate that alterations in T1W relaxation times, as measured by MRR, may serve as an early biomarker for Mn neurotoxicity. This neuroimaging approach exhibits remarkable accuracy in identifying Mn-susceptible brain regions, with a spatial resolution and sensitivity that surpasses current conventional dissection and mass spectrometry approaches. The capability to label and map TH and cFos expression across the entire brain provides insights into whole-brain neuronal activation and its connections to functional neural circuits and behavior following amphetamine and methylphenidate administration.

Keywords: manganese, environmental toxicology, dopamine dysfunction, biomarkers, drinking water, light sheet microscopy, magnetic resonance relaxometry (MRR)

Procedia PDF Downloads 20

Authors: David J. Foran, Nhan Do, Samuel Ajjarapu, Wenjin Chen, Tahsin Kurc, Joel H. Saltz

Abstract:

The large-scale data and computational requirements of investigators throughout the clinical and research communities demand an informatics infrastructure that supports both existing and new investigative and translational projects in a robust, secure environment. In some subspecialties of medicine and research, the capacity to generate data has outpaced the methods and technology used to aggregate, organize, access, and reliably retrieve this information. Leading health care centers now recognize the utility of establishing an enterprise-wide, clinical data warehouse. The primary benefits that can be realized through such efforts include cost savings, efficient tracking of outcomes, advanced clinical decision support, improved prognostic accuracy, and more reliable clinical trials matching. The overarching objective of the work presented here is the development and implementation of a flexible Intelligent Retrieval and Interrogation System (IRIS) that exploits the combined use of computational imaging, genomics, and data-mining capabilities to facilitate clinical assessments and translational research in oncology. The proposed System includes a multi-modal, Clinical & Research Data Warehouse (CRDW) that is tightly integrated with a suite of computational and machine-learning tools to provide insight into the underlying tumor characteristics that are not be apparent by human inspection alone. A key distinguishing feature of the System is a configurable Extract, Transform and Load (ETL) interface that enables it to adapt to different clinical and research data environments. This project is motivated by the growing emphasis on establishing Learning Health Systems in which cyclical hypothesis generation and evidence evaluation become integral to improving the quality of patient care. To facilitate iterative prototyping and optimization of the algorithms and workflows for the System, the team has already implemented a fully functional Warehouse that can reliably aggregate information originating from multiple data sources including EHR’s, Clinical Trial Management Systems, Tumor Registries, Biospecimen Repositories, Radiology PAC systems, Digital Pathology archives, Unstructured Clinical Documents, and Next Generation Sequencing services. The System enables physicians to systematically mine and review the molecular, genomic, image-based, and correlated clinical information about patient tumors individually or as part of large cohorts to identify patterns that may influence treatment decisions and outcomes. The CRDW core system has facilitated peer-reviewed publications and funded projects, including an NIH-sponsored collaboration to enhance the cancer registries in Georgia, Kentucky, New Jersey, and New York, with machine-learning based classifications and quantitative pathomics, feature sets. The CRDW has also resulted in a collaboration with the Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC) at the U.S. Department of Veterans Affairs to develop algorithms and workflows to automate the analysis of lung adenocarcinoma. Those studies showed that combining computational nuclear signatures with traditional WHO criteria through the use of deep convolutional neural networks (CNNs) led to improved discrimination among tumor growth patterns. The team has also leveraged the Warehouse to support studies to investigate the potential of utilizing a combination of genomic and computational imaging signatures to characterize prostate cancer. The results of those studies show that integrating image biomarkers with genomic pathway scores is more strongly correlated with disease recurrence than using standard clinical markers.

Keywords: clinical data warehouse, decision support, data-mining, intelligent databases, machine-learning.

Procedia PDF Downloads 132