Search results for: deep supervision

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 150

Authors: Rohini Das, Subhasish Das, Smruti Rekha Sahoo, Shagupta Yesmin

Abstract:

The Paleoproterozoic Kolhan Group (Purana) ensemble constitutes the youngest lithostratigraphic 'outlier' in the Singhbhum Archaean craton. The Kolhan unconformably overlies both the Singhbhum granite and the Iron Ore Group (IOG). Representing a typical sandstone-shale ( +/- carbonates) sequence, the Kolhan is characterized by the development of thin and discontinuous patches of basal conglomerates draped by sandstone beds. The IOG-fault limits the western 'distal' margin of the Kolhan basin showing evidence of passive subsidence subsequent to the initial rifting stage. The basin evolved as a half-graben under the influence of an extensional stress regime. The assumption of a tectonic setting for the NE-SW trending Kolhan basin possibly relates to the basin opening to the E-W extensional stress system that prevailed during the development of the Newer Dolerite dyke. The Paleoproterozoic age of the Kolhan basin is based on the consideration of the conformable stress pattern responsible both for the basin opening and the development of the conjugate fracture system along which the Newer Dolerite dykes intruded the Singhbhum Archaean craton. The Kolhan sandstones show progressive change towards greater textural and mineralogical maturity in its upbuilding. The trend of variations in different mineralogical and textural attributes, however, exhibits inflections at different lithological levels. Petrological studies collectively indicate that the sandstones were dominantly derived from a weathered granitic crust under a humid climatic condition. Provenance-derived variations in sandstone compositions are therefore a key in unraveling regional tectonic histories. The basin axis controlled the progradation direction which was likely driven by climatically induced sediment influx, a eustatic fall, or both. In the case of the incongruent shift, increased sediment supply permitted the rivers to cross the basinal deep. Temporal association of the Kolhan with tectonic structures in the belt indicates that syn-tectonic thrust uplift, not isostatic uplift or climate, caused the influx of quartz. The sedimentation pattern in the Kolhan reflects a change from braided fluvial-ephemeral pattern to a fan-delta-lacustrine type. The channel geometries and the climate exerted a major control on the processes of sediment transfer. Repeated fault controlled uplift of the source followed by subsidence and forced regression, generated multiple sediment cyclicity that led to the fluvial-fan delta sedimentation pattern. Intermittent uplift of the faulted blocks exposed fresh bedrock to mechanical weathering that generated a large amount of detritus and resulted to forced regressions, repeatedly disrupting the cycles which may reflect a stratigraphic response of connected rift basins at the early stage of extension. The marked variations in the thickness of the fan delta succession and the stacking pattern in different measured profiles reflect the overriding tectonic controls on fan delta evolution. The accumulated fault displacement created higher accommodation and thicker delta sequences. Intermittent uplift of fault blocks exposed fresh bedrock to mechanical weathering, generated a large amount of detritus, and resulted in forced closure of the land-locked basin, repeatedly disrupting the fining upward pattern. The control of source rock lithology or climate was of secondary importance to tectonic effects. Such a retrograding fan delta could be a stratigraphic response of connected rift basins at the early stage of extension.

Keywords: Kolhan basin, petrology, sandstone, tectonics

Procedia PDF Downloads 504

Authors: Ali Kazemi

Abstract:

Those within the volatile and interconnected international economic markets, appropriately predicting market trends, hold substantial fees for traders and financial establishments. Traditional device mastering strategies have made full-size strides in forecasting marketplace movements; however, monetary data's complicated and networked nature calls for extra sophisticated processes. This observation offers a groundbreaking method for monetary marketplace prediction that leverages the synergistic capability of Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks. Our suggested algorithm is meticulously designed to forecast the traits of inventory market indices and cryptocurrency costs, utilizing a comprehensive dataset spanning from January 1, 2015, to December 31, 2023. This era, marked by sizable volatility and transformation in financial markets, affords a solid basis for schooling and checking out our predictive version. Our algorithm integrates diverse facts to construct a dynamic economic graph that correctly reflects market intricacies. We meticulously collect opening, closing, and high and low costs daily for key inventory marketplace indices (e.g., S&P 500, NASDAQ) and widespread cryptocurrencies (e.g., Bitcoin, Ethereum), ensuring a holistic view of marketplace traits. Daily trading volumes are also incorporated to seize marketplace pastime and liquidity, providing critical insights into the market's shopping for and selling dynamics. Furthermore, recognizing the profound influence of the monetary surroundings on financial markets, we integrate critical macroeconomic signs with hobby fees, inflation rates, GDP increase, and unemployment costs into our model. Our GCN algorithm is adept at learning the relational patterns amongst specific financial devices represented as nodes in a comprehensive market graph. Edges in this graph encapsulate the relationships based totally on co-movement styles and sentiment correlations, enabling our version to grasp the complicated community of influences governing marketplace moves. Complementing this, our LSTM algorithm is trained on sequences of the spatial-temporal illustration discovered through the GCN, enriched with historic fee and extent records. This lets the LSTM seize and expect temporal marketplace developments accurately. Inside the complete assessment of our GCN-LSTM algorithm across the inventory marketplace and cryptocurrency datasets, the version confirmed advanced predictive accuracy and profitability compared to conventional and opportunity machine learning to know benchmarks. Specifically, the model performed a Mean Absolute Error (MAE) of 0.85%, indicating high precision in predicting day-by-day charge movements. The RMSE was recorded at 1.2%, underscoring the model's effectiveness in minimizing tremendous prediction mistakes, which is vital in volatile markets. Furthermore, when assessing the model's predictive performance on directional market movements, it achieved an accuracy rate of 78%, significantly outperforming the benchmark models, averaging an accuracy of 65%. This high degree of accuracy is instrumental for techniques that predict the course of price moves. This study showcases the efficacy of mixing graph-based totally and sequential deep learning knowledge in economic marketplace prediction and highlights the fee of a comprehensive, records-pushed evaluation framework. Our findings promise to revolutionize investment techniques and hazard management practices, offering investors and economic analysts a powerful device to navigate the complexities of cutting-edge economic markets.

Keywords: financial market prediction, graph convolutional networks (GCNs), long short-term memory (LSTM), cryptocurrency forecasting

Procedia PDF Downloads 66

Authors: P. C. Kutschera, Elena C. Tesoro, Mary Grace Talamera-Sandico, Jose Maria G. Pelayo III

Abstract:

Second generation military Filipino Amerasians comprise a formidable contemporary segment of the estimated 250,000-plus biracial Amerasians in the Philippines today. Overall, they are a stigmatized and socioeconomically marginalized diaspora, historically; they were abandoned or estranged by U.S. military personnel fathers assigned during the century-long Colonial, Post-World War II and Cold War Era of permanent military basing (1898-1992). Indeed, U.S. military personnel remain stationed in smaller numbers in the Philippines today. This inquiry is an outgrowth of two recent small sample studies. The first surfaced the impact of the U.S. military prostitution system on formation of the ‘Derivative Amerasian Family Construct’ on first generation Amerasians; a second, qualitative case study suggested the continued effect of the prostitution systems' destructive impetuous on second generation Amerasians. The intent of this current qualitative, multiple-case study was to actively seek out second generation sex industry toilers. The purpose was to focus further on this human phenomenon in the post-basing and post-military prostitution system eras. As background, the former military prostitution apparatus has transformed into a modern dynamic of rampant sex tourism and prostitution nationwide. This is characterized by hotel and resorts offering unrestricted carnal access, urban and provincial brothels (casas), discos, bars and pickup clubs, massage parlors, local barrio karaoke bars and street prostitution. A small case study sample (N = 4) of female and male second generation Amerasians were selected. Sample formation employed a non-probability ‘snowball’ technique drawing respondents from the notorious Angeles, Metro Manila, Olongapo City ‘AMO Amerasian Triangle’ where most former U.S. military installations were sited and modern sex tourism thrives. A six-month study and analysis of in-depth interviews of female and male sex laborers, their families and peers revealed a litany of disturbing, and troublesome experiences. Results showed profiles of debilitating human poverty, history of family disorganization, stigmatization, social marginalization and the ghost of the military prostitution system and its harmful legacy on Amerasian family units. Emerging were testimonials of wayward young people ensnared in a maelstrom of deep economic deprivation, familial dysfunction, psychological desperation and societal indifference. The paper recommends that more study is needed and implications of unstudied psychosocial and socioeconomic experiences of distressed younger generations of military Amerasians require specific research. Heretofore apathetic or disengaged U.S. institutions need to confront the issue and formulate activist and solution-oriented social welfare, human services and immigration easement policies and alternatives. These institutions specifically include academic and social science research agencies, corporate foundations, the U.S. Congress, and Departments of State, Defense and Health and Human Services, and Homeland Security (i.e. Citizen and Immigration Services) It is them who continue to endorse a laissez-faire policy of non-involvement over the entire Filipino Amerasian question. Such apathy, the paper concludes, relegates this consequential but neglected blood progeny to the status of humiliating destitution and exploitation. Amerasians; thus, remain entrapped in their former colonial, and neo-colonial habitat. Ironically, they are unwitting victims of a U.S. American homeland that fancies itself geo-politically as a strong and strategic military treaty ally of the Philippines in the Western Pacific.

Keywords: Asian Americans, diaspora, Filipino Amerasians, military prostitution, stigmatization

Procedia PDF Downloads 487

Authors: Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

Abstract:

Time series data consist of successive data points collected over a period of time. Accurate prediction of future values is essential for informed decision-making in several real-world applications, including electricity load demand forecasting, lifetime estimation of industrial machinery, traffic planning, weather prediction, and the stock market. Due to their critical relevance and wide application, there has been considerable interest in time series forecasting in recent years. However, the proliferation of sensors and IoT devices, real-time monitoring systems, and high-frequency trading data introduce significant intricate temporal variations, rapid changes, noise, and non-linearities, making time series forecasting more challenging. Classical methods such as Autoregressive integrated moving average (ARIMA) and Exponential Smoothing aim to extract pre-defined temporal variations, such as trends and seasonality. While these methods are effective for capturing well-defined seasonal patterns and trends, they often struggle with more complex, non-linear patterns present in real-world time series data. In recent years, deep learning has made significant contributions to time series forecasting. Recurrent Neural Networks (RNNs) and their variants, such as Long short-term memory (LSTMs) and Gated Recurrent Units (GRUs), have been widely adopted for modeling sequential data. However, they often suffer from the locality, making it difficult to capture local trends and rapid fluctuations. Convolutional Neural Networks (CNNs), particularly Temporal Convolutional Networks (TCNs), leverage convolutional layers to capture temporal dependencies by applying convolutional filters along the temporal dimension. Despite their advantages, TCNs struggle with capturing relationships between distant time points due to the locality of one-dimensional convolution kernels. Transformers have revolutionized time series forecasting with their powerful attention mechanisms, effectively capturing long-term dependencies and relationships between distant time points. However, the attention mechanism may struggle to discern dependencies directly from scattered time points due to intricate temporal patterns. Lastly, Multi-Layer Perceptrons (MLPs) have also been employed, with models like N-BEATS and LightTS demonstrating success. Despite this, MLPs often face high volatility and computational complexity challenges in long-horizon forecasting. To address intricate temporal variations in time series data, this study introduces Times2D, a novel framework that parallelly integrates 2D spectrogram and derivative heatmap techniques. The spectrogram focuses on the frequency domain, capturing periodicity, while the derivative patterns emphasize the time domain, highlighting sharp fluctuations and turning points. This 2D transformation enables the utilization of powerful computer vision techniques to capture various intricate temporal variations. To evaluate the performance of Times2D, extensive experiments were conducted on standard time series datasets and compared with various state-of-the-art algorithms, including DLinear (2023), TimesNet (2023), Non-stationary Transformer (2022), PatchTST (2023), N-HiTS (2023), Crossformer (2023), MICN (2023), LightTS (2022), FEDformer (2022), FiLM (2022), SCINet (2022a), Autoformer (2021), and Informer (2021) under the same modeling conditions. The initial results demonstrated that Times2D achieves consistent state-of-the-art performance in both short-term and long-term forecasting tasks. Furthermore, the generality of the Times2D framework allows it to be applied to various tasks such as time series imputation, clustering, classification, and anomaly detection, offering potential benefits in any domain that involves sequential data analysis.

Keywords: derivative patterns, spectrogram, time series forecasting, times2D, 2D representation

Procedia PDF Downloads 42

Authors: Manavjit Singh Dhindsa, Ursula Das, Kshirasagar Naik, Marzia Zaman, Richard Purcell, Srinivas Sampalli, Abdul Mutakabbir, Chung-Horng Lung, Thambirajah Ravichandran

Abstract:

These days, wildland fires, also known as forest fires, are more prevalent than ever. Wildfires have major repercussions that affect ecosystems, communities, and the environment in several ways. Wildfires lead to habitat destruction and biodiversity loss, affecting ecosystems and causing soil erosion. They also contribute to poor air quality by releasing smoke and pollutants that pose health risks, especially for individuals with respiratory conditions. Wildfires can damage infrastructure, disrupt communities, and cause economic losses. The economic impact of firefighting efforts, combined with their direct effects on forestry and agriculture, causes significant financial difficulties for the areas impacted. This research explores different forest fire spread models and presents a comprehensive review of various techniques and methodologies used in the field. A forest fire spread model is a computational or mathematical representation that is used to simulate and predict the behavior of a forest fire. By applying scientific concepts and data from empirical studies, these models attempt to capture the intricate dynamics of how a fire spreads, taking into consideration a variety of factors like weather patterns, topography, fuel types, and environmental conditions. These models assist authorities in understanding and forecasting the potential trajectory and intensity of a wildfire. Emphasizing the need for a comprehensive understanding of wildfire dynamics, this research explores the approaches, assumptions, and findings derived from various models. By using a comparison approach, a critical analysis is provided by identifying patterns, strengths, and weaknesses among these models. The purpose of the survey is to further wildfire research and management techniques. Decision-makers, researchers, and practitioners can benefit from the useful insights that are provided by synthesizing established information. Fire spread models provide insights into potential fire behavior, facilitating authorities to make informed decisions about evacuation activities, allocating resources for fire-fighting efforts, and planning for preventive actions. Wildfire spread models are also useful in post-wildfire mitigation strategies as they help in assessing the fire's severity, determining high-risk regions for post-fire dangers, and forecasting soil erosion trends. The analysis highlights the importance of customized modeling approaches for various circumstances and promotes our understanding of the way forest fires spread. Some of the known models in this field are Rothermel’s wildland fuel model, FARSITE, WRF-SFIRE, FIRETEC, FlamMap, FSPro, cellular automata model, and others. The key characteristics that these models consider include weather (includes factors such as wind speed and direction), topography (includes factors like landscape elevation), and fuel availability (includes factors like types of vegetation) among other factors. The models discussed are physics-based, data-driven, or hybrid models, also utilizing ML techniques like attention-based neural networks to enhance the performance of the model. In order to lessen the destructive effects of forest fires, this initiative aims to promote the development of more precise prediction tools and effective management techniques. The survey expands its scope to address the practical needs of numerous stakeholders. Access to enhanced early warning systems enables decision-makers to take prompt action. Emergency responders benefit from improved resource allocation strategies, strengthening the efficacy of firefighting efforts.

Keywords: artificial intelligence, deep learning, forest fire management, fire risk assessment, fire simulation, machine learning, remote sensing, wildfire modeling

Procedia PDF Downloads 81

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 126