Large Language Models (LLMs) have shown remarkable success in supporting a wide range of knowledge-intensive tasks. In specialized domains, there is growing interest in leveraging LLMs to assist subject matter experts with domain-specific challenges. However, deploying LLMs as SaaS solutions raises data privacy concerns, while many open-source models demand significant computational resources for effective domain adaptation and deployment. A promising alternative is to develop smaller, domain-specialized LLMs, though this approach is often constrained by the lack of high-quality domain-specific training data. In this work, we address these limitations by presenting a cost-efficient and scalable training pipeline that combines guided synthetic data generation from a small seed corpus with bottom-up domain data curation. Our pipeline integrates Domain-Adaptive Pretraining (DAPT), Domain-specific Supervised Fine-tuning (DSFT), and Direct Preference Optimization (DPO) to train effective small-scale models for specialized use cases. We demonstrate this approach through DiagnosticSLM, a 3B-parameter domain-specific model tailored for fault diagnosis, root cause analysis, and repair recommendation in industrial settings. To evaluate model performance, we introduce four domain-specific benchmarks: multiple-choice questions (DiagnosticMCQ), question answering (DiagnosticQA), sentence completion (DiagnosticComp), and summarization (DiagnosticSum). DiagnosticSLM achieves up to 25% accuracy improvement over open-source models of comparable or larger size (2B-9B) on the MCQ task, while also outperforming or matching them in other tasks, demonstrating effective domain-specific reasoning and generalization capabilities.

In this paper, we propose a novel approach for probabilistic time series modeling using deep learning, capitalizing on the flexibility of Functional Neural Networks (FNNs) and the benefits of residual blocks along with dropout. The inherent versatility of FNNs allows for seamless integration of dropout and residual blocks, which enhances the model’s capability to capture uncertainty and complex temporal patterns. First, we introduce a new architecture, ResFNN, an FNN with residual blocks, which improves model depth and stability while avoiding issues such as vanishing gradients. Next, we incorporate dropout (DP), ResFNN DP, to achieve probabilistic modeling for any time series task, offering valuable insights into model performance along with confidence intervals. Our method is evaluated on Walmart Store Sales time series dataset, demonstrating that ResFNN DP outperforms state-of-the-art models in terms of predictive accuracy and uncertainty quantification. The flexibility of FNN, combined with the strengths of residual learning and dropout, positions ResFNN DP as a powerful framework for probabilistic time series analysis.

Dynamic dispatching rules that allocate resources to tasks in real-time play a critical role in ensuring efficient operations of many automated material handling systems across industries. Traditionally, the dispatching rules deployed are typically the result of manually crafted heuristics based on domain experts’ knowledge. Generating these rules is time-consuming and often sub-optimal. As enterprises increasingly accumulate vast amounts of operational data, there is significant potential to leverage this big data to enhance the performance of automated systems. One promising approach is to use Decision Transformers, which can be trained on existing enterprise data to learn better dynamic dispatching rules for improving system throughput. In this work, we study the application of Decision Transformers as dynamic dispatching policies within an actual multi-agent material handling system and identify scenarios where enterprises can effectively leverage Decision Transformers on existing big data to gain business value. Our empirical results demonstrate that Decision Transformers can improve the material handling system’s throughput by a considerable amount when the heuristic originally used in the enterprise data exhibits moderate performance and involves no randomness. When the original heuristic has strong performance, Decision Transformers can still improve the throughput but with a smaller improvement margin. However, when the original heuristics contain an element of randomness or when the performance of the dataset is below a certain threshold, Decision Transformers fail to outperform the original heuristic. These results highlight both the potential and limitations of Decision Transformers as dispatching policies for automated industrial material handling systems.

The rise in data has led to the need for dimension reduction techniques, especially in the area of non-scalar variables, including time series, natural language processing, and computer vision. In this paper, we specifically investigate dimension reduction for time series through functional data analysis. Current methods for dimension reduction in functional data are functional principal component analysis and functional autoencoders, which are limited to linear mappings or scalar representations for the time series, which is inefficient. In real data applications, the nature of the data is much more complex. We propose a non-linear function-on-function approach, which consists of a functional encoder and a functional decoder, that uses continuous hidden layers consisting of continuous neurons to learn the structure inherent in functional data, which addresses the aforementioned concerns in the existing approaches. Our approach gives a low dimension latent representation by reducing the number of functional features as well as the timepoints at which the functions are observed. The effectiveness of the proposed model is demonstrated through multiple simulations and real data examples.

Development of an accurate, flexible, and numerically efficient uncertainty quantification (UQ) method is one of fundamental challenges in machine learning. Previously, a UQ method called DISCO Nets has been proposed (Bouchacourt et al., 2016), which trains a neural network by minimizing the energy score. In this method, a random noise vector in $\mathbb{R}^{10\text{--}100}$ is concatenated with the original input vector in order to produce a diverse ensemble forecast despite using a single neural network. While this method has shown promising performance on a hand pose estimation task in computer vision, it remained unexplored whether this method works as nicely for regression on tabular data, and how it competes with more recent advanced UQ methods such as NGBoost. In this paper, we propose an improved neural architecture of DISCO Nets that admits faster and more stable training while only using a compact noise vector of dimension $\sim \mathcal{O}(1)$. We benchmark this approach on miscellaneous real-world tabular datasets and confirm that it is competitive with or even superior to standard UQ baselines. Moreover we observe that it exhibits better point forecast performance than a neural network of the same size trained with the conventional mean squared error. As another advantage of the proposed method, we show that local feature importance computation methods such as SHAP can be easily applied to any subregion of the predictive distribution. A new elementary proof for the validity of using the energy score to learn predictive distributions is also provided.

Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty. Disentangling and evaluating these uncertainties simultaneously stands a chance of improving the agent's final performance, accelerating training, and facilitating quality assurance after deployment. In this work, we propose an uncertainty-aware reinforcement learning algorithm for continuous control tasks that extends the Deep Deterministic Policy Gradient algorithm (DDPG). It exploits epistemic uncertainty to accelerate exploration and aleatoric uncertainty to learn a risk-sensitive policy. We conduct numerical experiments showing that our variant of DDPG outperforms vanilla DDPG without uncertainty estimation in benchmark tasks on robotic control and power-grid optimization.

Traditionally, the performance of multi-agent deep reinforcement learning algorithms are demonstrated and validated in gaming environments where we often have a fixed number of agents. In many industrial applications, the number of available agents can change at any given day and even when the number of agents is known ahead of time, it is common for an agent to break during the operation and become unavailable for a period of time. In this paper, we propose a new deep reinforcement learning algorithm for multi-agent collaborative tasks with a variable number of agents. We demonstrate the application of our algorithm using a fleet management simulator developed by Hitachi to generate realistic scenarios in a production site.

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on real-world physical systems remains limited. Despite the advancements in RL algorithms, the industries often prefer traditional control strategies. Traditional methods are simple, computationally efficient and easy to adjust. In this paper, we first propose a new Q-learning algorithm for continuous action space, which can bridge the control and RL algorithms and bring us the best of both worlds. Our method can learn complex policies to achieve long-term goals and at the same time it can be easily adjusted to address short-term requirements without retraining. Next, we present an approximation of our algorithm which can be applied to address short-term requirements of any pre-trained RL algorithm. The case studies demonstrate that both our proposed method as well as its practical approximation can achieve short-term and long-term goals without complex reward functions.

Time series data have grown at an explosive rate in numerous domains and have stimulated a surge of time series modeling research. A comprehensive comparison of different time series models, for a considered data analytics task, provides useful guidance on model selection for data analytics practitioners. Data scarcity is a universal issue that occurs in a vast range of data analytics problems, due to the high costs associated with collecting, generating, and labeling data as well as some data quality issues such as missing data. In this paper, we focus on the temporal classification/regression problem that attempts to build a mathematical mapping from multivariate time series inputs to a discrete class label or a real-valued response variable. For this specific problem, we identify two types of scarce data: scarce data with small samples and scarce data with sparsely and irregularly observed time series covariates. Observing that all existing works are incapable of utilizing the sparse time series inputs for proper modeling building, we propose a model called sparse functional multilayer perceptron (SFMLP) for handling the sparsity in the time series covariates. The effectiveness of the proposed SFMLP under each of the two types of data scarcity, in comparison with the conventional deep sequential learning models (e.g., Recurrent Neural Network, and Long Short-Term Memory), is investigated through mathematical arguments and numerical experiments.

In the last few decades, building regression models for non-scalar variables, including time series, text, image, and video, has attracted increasing interests of researchers from the data analytic community. In this paper, we focus on a multivariate time series regression problem. Specifically, we aim to learn mathematical mappings from multiple chronologically measured numerical variables within a certain time interval S to multiple numerical variables of interest over time interval T. Prior arts, including the multivariate regression model, the Seq2Seq model, and the functional linear models, suffer from several limitations. The first two types of models can only handle regularly observed time series. Besides, the conventional multivariate regression models tend to be biased and inefficient, as they are incapable of encoding the temporal dependencies among observations from the same time series. The sequential learning models explicitly use the same set of parameters along time, which has negative impacts on accuracy. The function-on-function linear model in functional data analysis (a branch of statistics) is insufficient to capture complex correlations among the considered time series and suffer from under-fitting easily. In this paper, we propose a general functional mapping that embraces the function-on-function linear model as a special case. We then propose a non-linear function-on-function model using the fully connected neural network to learn the mapping from data, which addresses the aforementioned concerns in the existing approaches. For the proposed model, we describe in detail the corresponding numerical implementation procedures. The effectiveness of the proposed model is demonstrated through the application to two real-world problems.

Dynamic dispatching is one of the core problems for operation optimization in traditional industries such as mining, as it is about how to smartly allocate the right resources to the right place at the right time. Conventionally, the industry relies on heuristics or even human intuitions which are often short-sighted and sub-optimal solutions. Leveraging the power of AI and Internet of Things (IoT), data-driven automation is reshaping this area. However, facing its own challenges such as large-scale and heterogenous trucks running in a highly dynamic environment, it can barely adopt methods developed in other domains (e.g., ride-sharing). In this paper, we propose a novel Deep Reinforcement Learning approach to solve the dynamic dispatching problem in mining. We first develop an event-based mining simulator with parameters calibrated in real mines. Then we propose an experience-sharing Deep Q Network with a novel abstract state/action representation to learn memories from heterogeneous agents altogether and realizes learning in a centralized way. We demonstrate that the proposed methods significantly outperform the most widely adopted approaches in the industry by 5.56% in terms of productivity. The proposed approach has great potential in a broader range of industries (e.g., manufacturing, logistics) which have a large-scale of heterogenous equipment working in a highly dynamic environment, as a general framework for dynamic resource allocation.

Explosive growth in spatio-temporal data and its wide range of applications have attracted increasing interests of researchers in the statistical and machine learning fields. The spatio-temporal regression problem is of paramount importance from both the methodology development and real-world application perspectives. Given the observed spatially encoded time series covariates and real-valued response data samples, the goal of spatio-temporal regression is to leverage the temporal and spatial dependencies to build a mapping from covariates to response with minimized prediction error. Prior arts, including the convolutional Long Short-Term Memory (CovLSTM) and variations of the functional linear models, cannot learn the spatio-temporal information in a simple and efficient format for proper model building. In this work, we propose two novel extensions of the Functional Neural Network (FNN), a temporal regression model whose effectiveness and superior performance over alternative sequential models have been proven by many researchers. The effectiveness of the proposed spatio-temporal FNNs in handling varying spatial correlations is demonstrated in comprehensive simulation studies. The proposed models are then deployed to solve a practical and challenging precipitation prediction problem in the meteorology field.

In equipment health classification, machines in normal, degradation and critical stages are classified based on domain experts KPI (Remaining Useful Life). Higher KPI values indicate healthier machines. GANs can be used to generate sensor data for machines in different health stages. There are challenges for this type of sensor generation. Firstly, the generated samples for different health stages should be well separated. For example, it is not preferred that generated samples in critical stage have higher KPI values than generated samples in degradation stage. Secondly, sensor data in different stages are not equally different with each other. For instance, sensor data in normal stage is more like sensor data in degradation stage than that in critical stage. However, in existing GAN, data labels are represented using one-hot vectors and different between-class distances are not explicitly considered. We propose discriminant GANs, where, for generated samples, we maximize between-class distance and minimize within-class distance, so that generated samples in different classes are more separable and different betweenclass distances are explicitly allowed. Empirical experiments show that (1) discriminant regularization improves the quality of generated samples, (2) discriminant regularized GANs extract efficient features for equipment health classification.

Generative Adversarial Networks (GANs) have been shown effective to generate realistic enough sensor data for industrial failure prediction. Compared to computer vision problems, where it is very common to have more than 1000 classes, the number of classes for industrial problems is very small. For instance, only two classes, failure or non-failure, are considered in failure prediction. When using GANs to generate industrial sensor data, many of the generated samples are from the same class and thus are highly correlated. However, this relationships among generated samples are not explicitly considered in existing GAN frameworks. This type of correlations can be captured by trace norm minimization. In this work, we propose Trace Norm GANs to enforce trace norm minimization on generated samples. Extensive experiments on real industrial data show that (1) Trace Norm GANs improve generated samples in terms of quality/diversity metrics, (2) Trace Norm GANs extract efficient features for supervised learning tasks.

Industrial AI is concerned with the application of Artificial Intelligence (AI), Machine Learning (ML) and related technologies towards addressing real-world use cases in industrial and societal domains. These uses cases can be broadly categorized into the horizontal areas of maintenance and repair, operations and supply chain, quality, safety, design, and end-to-end optimization - with applications in a variety of verticals. In the last few years, we have witnessed a growing interest in applying Deep Learning (DL) techniques to Industrial AI problems, ranging from using sequence models such as Long Short-Term Memory (LSTM) for predicting failures in equipment, to using Deep Reinforcement Learning (Deep RL) for scheduling and dispatching. Applying deep learning techniques to industrial applications imposes a set of unique challenges, which include, but are not limited to, (1) limited data, highly skewed class distribution and occurrence of rare classes such as failures, (2) multi-modal data (sensors, events, images, text, etc.) indexed over space and time (3) the need for explainable decisions, (4) a need to attain consistency between different but "related" models and between multiple generations of the same model, and (5) decision making to optimize business outcomes where the cost of a mistake could be very high. This tutorial presents an overview of these challenges, along with new methods and best practices to address them. Examples of these methods include using sequence DL models and Functional Neural Networks (FNNs) for modeling sensor and spatiotemporal measurements; using multi-task learning, graph models and ensemble learning for improving consistency of DL models; using deep RL for health indicator learning and dynamic dispatching; cost-based decision making for prognostics; and using GANs for generating senor data for prognostics. Finally, we will present some open problems in Industrial AI and how the research community can shape the future of the next industrial and societal revolution.

Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From an AI model perspective it means given the same input the user would expect the same output, especially for correct outputs, or in other words consistently correct outputs. This paper studies a model behavior in the context of periodic retraining of deployed models where the outputs from successive generations of the models might not agree on the correct labels assigned to the same input. We formally define consistency and correct-consistency of a learning model. We prove that consistency and correct-consistency of an ensemble learner is not less than the average consistency and correct-consistency of individual learners and correct-consistency can be improved with a probability by combining learners with accuracy not less than the average accuracy of ensemble component learners. To validate the theory using three datasets and two state-of-the-art deep learning classifiers we also propose an efficient dynamic snapshot ensemble method and demonstrate its value. Code for our algorithm is available at https://github.com/christa60/dynens.

Operating envelope is an important concept in industrial operations. Accurate identification for operating envelope can be extremely beneficial to stakeholders as it provides a set of operational parameters that optimizes some key performance indicators (KPI) such as product quality, operational safety, equipment efficiency, environmental impact, etc. Given the importance, data-driven approaches for computing the operating envelope are gaining popularity. These approaches typically use classifiers such as support vector machines, to set the operating envelope by learning the boundary in the operational parameter spaces between the manually assigned `large KPI' and `small KPI' groups. One challenge to these approaches is that the assignment to these groups is often ad-hoc and hence arbitrary. However, a bigger challenge with these approaches is that they don't take into account two key features that are needed to operationalize operating envelopes: (i) interpretability of the envelope by the operator and (ii) implementability of the envelope from a practical standpoint. In this work, we propose a new definition for operating envelope which directly targets the expected magnitude of KPI (i.e., no need to arbitrarily bin the data instances into groups) and accounts for the interpretability and the implementability. We then propose a regularized `GA +penalty' algorithm that outputs an envelope where the user can tradeoff between bias and variance. The validity of our proposed algorithm is demonstrated by two sets of simulation studies and an application to a real-world challenge in the mining processes of a flotation plant.

Monitoring and understanding the performance of equipment and operations is a real and challenging problem in industrial and commercial settings. Although many operations have a set of agreed-upon Key Performance Indicators (KPIs) that have been defined by domain experts, most of these KPIs suffer from many issues including but not limited to sensitivity to seasonality and load conditions, approximate and inaccurate calculations, and measurement noise. This makes further analysis of these measurements a real challenge. This paper focuses on answering a simple yet crucial question in regards to KPI monitoring: "Have a given event made an impact on the performance of an operation?". The paper presents an approach to answer this question in a systematic and statistically-sound way while alleviating the aforementioned problems with the provided KPIs. The key idea behind the proposed approach is to predict the would-be performance as if the event has not happened. The approach then applies a three-way hypothesis testing on the difference between the would-be and actual performance to determine whether the event resulted in improvement, degradation or no-change in performance. Results from simulation study and experiments on real use cases demonstrate the effectiveness and usability of the proposed approach.

Equipment-as-a-service is gaining popularity in industries as it provides the customers with high flexibility and scalability and allows the service provider to optimize operations so that both the service provider and the customers are benefited. However, pricing modeling is a critical challenge in EaaS due to the change of business objectives from selling products to providing services. Particularly, EaaS faces severe high-cost issues as unexpected equipment failures can result in expensive downtime costs. In this paper, we take advantage of Failure Prediction (FP) in Predictive Maintenance (PdM) domain and Dynamic Pricing to build a hybrid model that balances cost and benefit for EaaS. First, we build a Gradient Boosting based FP model to predict failure probabilities. Then a Risk-based Dynamic Pricing (RBDP) model uses the confusion matrix of FP to estimate the cost effects of predicted failures with a constrained objective function. Finally, the FP model and RBDP model are trained simultaneously to minimize the objective function so that it compensates for the failure cost and maximize the overall profit gain. The proposed hybrid modeling approach is compared with traditional FP without pricing policy approach, and FP with a static pricing policy approach to show significant improvements in profit increases.

In this paper, we propose a novel algorithm for generalizing Multilayer Perceptron (MLP) to handle sparse functional data, wherein for a given subject there are multiple observations available over time and these observations are sparsely and irregularly distributed within the considered time range. The algorithm uses pooled observations across all the subjects to estimate a set of basis functions for the underlying correlation between time steps and then use these basis functions to build a sparse functional neuron that extracts features for each subject. We justify the validity of our algorithm through theoretical arguments. We also demonstrate the use of the proposed algorithm in solving three data challenges: the classification of synthetic curves, the prediction of patient's long-term survival, and the estimation of the remaining time to critical failures for turbofan engines. To show the superiority of our algorithm under sparse functional data scenarios, we compare the performance of our model with two alternative common practices, and demonstrate that our method outperforms the baseline methods in all numerical studies.

One of the key challenges in predictive maintenance is to predict the impending downtime of an equipment with a reasonable prediction horizon so that countermeasures can be put in place. Classically, this problem has been posed in two different ways which are typically solved independently: (1) Remaining useful life (RUL) estimation as a long-term prediction task to estimate how much time is left in the useful life of the equipment and (2) Failure prediction (FP) as a short-term prediction task to assess the probability of a failure within a pre-specified time window. As these two tasks are related, performing them separately is sub-optimal and might results in inconsistent predictions for the same equipment. In order to alleviate these issues, we propose two methods: Deep Weibull model (DW-RNN) and multi-task learning (MTL-RNN). DW-RNN is able to learn the underlying failure dynamics by fitting Weibull distribution parameters using a deep neural network, learned with a survival likelihood, without training directly on each task. While DW-RNN makes an explicit assumption on the data distribution, MTL-RNN exploits the implicit relationship between the long-term RUL and short-term FP tasks to learn the underlying distribution. Additionally, both our methods can leverage the non-failed equipment data for RUL estimation. We demonstrate that our methods consistently outperform baseline RUL methods that can be used for FP while producing consistent results for RUL and FP. We also show that our methods perform at par with baselines trained on the objectives optimized for either of the two tasks.

For many industrial and commercial operations,maintenance accounts for a large part of operating costs (e.g., 15%-60% of the total production costs in manufacturing plants). Even with maintenance cost being such a substantial part of the overall cost, maintenance managers have little visibility into whether maintenance expenditure is money well spent or not. They also do not have standard quantitative methods to answer even simple questions such as, does it make any difference if one does preventive maintenance every six months on a piece of equipment, or whether a particular maintenance action is improving the performance of an equipment or not. In this paper, we formally define the problem of estimating the effectiveness of a single or a group of maintenance actions, and propose a systemic way of solving the problem. We also present a benchmark to evaluate the proposed methods and demonstrate how they can accurately identify effective maintenance actions.

Open pit mining operations require utilization of extremely expensive equipment such as large trucks, shovels and loaders. To remain competitive, mining companies are under pressure to increase equipment utilization and reduce operational costs. The key to this in mining operations is to have sophisticated truck assignment strategies which will ensure that equipment is utilized efficiently with minimum operating cost. To address this problem, we have implemented truck assignment approach which integrates machine learning, linear/integer programming and simulation. Our truck assignment approach takes into consideration the number of trucks and their sizes, shovels and dump locations as well as stochastic activity times during the operations. Machine learning is used to predict probability distributions of equipment activity duration. We have validated the approach using data collected from two open pit mines. Our experimental results show that our approach offers increase of 10% in efficiency. Presented results demonstrate that machine learning can bring significant value to mining industry.

Complex Event Processing (CEP) has become increasingly important for tracking and monitoring anomalies and trends in event streams emitted from business processes such as supply chain management to online stores in e-commerce. These monitoring applications submit complex event queries to track sequences of events that match a given pattern. While the state-of-the-art CEP systems mostly focus on the execution of flat sequence queries, we instead support the execution of nested CEP queries specified by the (NEsted Event Language) NEEL. However the iterative execution often results in the repeated recomputation of similar or even identical results for nested subexpressions as the window slides over the event stream. In this work we thus propose to optimize NEEL execution performance by caching intermediate results. In particular we design two methods of applying selective caching of intermediate results. The first is the Continuous Sliding Caching technique. The second is a further optimization of the previous technique which we call the Interval-Driven Semantic Caching. Techniques for incrementally loading, purging and exploiting the cache content are described. Our experimental study using real-world stock trades evaluates the performance of our proposed caching strategies for different query types.

The advances in sensor technologies enable real-time collection of high-fidelity spatiotemporal data on transportation networks of major cities. In this paper, using two real-world transportation datasets: 1) incident data and 2) traffic data, we address the problem of predicting and quantifying the impact of traffic incidents. Traffic incidents include any non-recurring events on road networks, including accidents, weather hazard, road construction or work zone closures. By analyzing archived incident data, we classify incidents based on their features (e.g., time, location, type of incident). Subsequently, we model the impact of each incident class on its surrounding traffic by analyzing the archived traffic data at the time and location of the incidents. Consequently, in real-time, if we observe a similar incident (from real-time incident data), we can predict and quantify its impact on the surrounding traffic using our developed models. This information, in turn, can help drivers to effectively avoid impacted areas in real-time. To be useful for such real-time navigation application, and unlike current approaches, we study the dynamic behavior of incidents and model the impact as a quantitative time varying spatial span. In addition to utilizing incident features, we improve our classification approach further by analyzing traffic density around the incident area and the initial behavior of the incident. We evaluated our approach with very large traffic and incident datasets collected from the road networks of Los Angeles County and the results show that we can improve our baseline approach, which solely relies on incident features, by up to 45%.

Complex Event Processing (CEP) over event streams has become increasingly important for real-time applications ranging from healthcare to supply chain management. In such applications, arbitrarily complex sequence patterns as well as non existence of such complex situations must be detected in real time. To assure real-time responsiveness for detection of such complex pattern over high volume high-speed streams, efficient processing techniques must be designed. Unfortunately the efficient processing of complex sequence queries with negations remains a largely open problem to date. To tackle this shortcoming, we designed optimized strategies for handling nested CEP query. In this demonstration, we propose to showcase these techniques for processing and optimizing nested pattern queries on streams. In particular our demonstration showcases a platform for specifying complex nested queries, and selecting one of the alternative optimized techniques including sub-expression sharing and intermediate result caching to process them. We demonstrate the efficiency of our optimized strategies by graphically comparing the execution time of the optimized solution against that of the default processing strategy of nested CEP queries. We also demonstrate the usage of the proposed technology in several healthcare services.

Complex event processing (CEP) over event streams has become increasingly important for real-time applications ranging from health care, supply chain management to business intelligence. These monitoring applications submit complex queries to track sequences of events that match a given pattern. As these systems mature the need for increasingly complex nested sequence query support arises, while the state-of-art CEP systems mostly support the execution of flat sequence queries only. To assure real-time responsiveness and scalability for pattern detection even on huge volume high-speed streams, efficient processing techniques must be designed. In this paper, we first analyze the prevailing nested pattern query processing strategy and identify several serious shortcomings. Not only are substantial subsequences first constructed just to be subsequently discarded, but also opportunities for shared execution of nested subexpressions are overlooked. As foundation, we introduce NEEL, a CEP query language for expressing nested CEP pattern queries composed of sequence, negation, AND and OR operators. To overcome deficiencies, we design rewriting rules for pushing negation into inner subexpressions. Next, we devise a normalization procedure that employs these rules for flattening a nested complex event expression. To conserve CPU and memory consumption, we propose several strategies for efficient shared processing of groups of normalized NEEL subexpressions. These strategies include prefix caching, suffix clustering and customized “bit-marking” execution strategies. We design an optimizer to partition the set of all CEP subexpressions in a NEEL normal form into groups, each of which can then be mapped to one of our shared execution operators. Lastly, we evaluate our technologies by conducting a performance study to assess the CPU processing time using real-world stock trades data. Our results confirm that our NEEL execution in many cases performs 100 fold faster than the traditional iterative nested execution strategy for real stock market query workloads.

Due to copyright restrictions, the access to the full text of this article is only available via subscription.

In streaming and sensor data applications, the problems of synopsis construction and outlier detection are important. Due to their low complexity, desirable properties and relative ease of understanding, wavelet based techniques are often used for both synopsis construction and anomaly detection. In streaming data literature, Mallat's algorithm is often used to achieve a Haar wavelet decomposition in O(n) time. However, there is one limitation to this popular technique, in that it leads to a dyadic decomposition of data. We demonstrate that the property of non-dyadicity is of considerable use in synopsis construction and anomaly detection. In this regard we present several application results, a synopsis data structure for streaming data that is an order of magnitude superior to the popular Haar based wavelet technique, a method for finding anomalies for sensor data over non-dyadic hierarchies, etc. In our work, we enable non-dyadicity by proposing a Mallat like construction for a wavelet system that admits non-dyadic basis. Our algorithm builds a non-dyadic hierarchical structure, and is more efficient than the state of the art construction. We prove the correctness of our construction by showing that our basis functions demonstrates the properties of a wavelet system.

Many modern applications including tag based mass transit systems, RFID-based supply chain management systems and online financial feeds require special purpose event stream processing technology to analyze vast amounts of sequential multi-dimensional data available in real-time data feeds. Traditional online analytical processing (OLAP) systems are not designed for real-time pattern-based operations, while Complex Event Processing (CEP) systems are designed for sequence detection and do not support OLAP operations. We will demonstrate a novel E-Cube model that combines CEP and OLAP techniques for multi-dimensional event pattern analysis at different abstraction levels. A London transit scenario will be given to demonstrate the utility and performance of this proposed technology.

Emerging business intelligence (BI) applications aim to provide situational awareness, i.e., information about real-world events that might affect the business operations of an enterprise. For instance, an enterprise might want to know whether customers are posting positive or negative comments about a new product it has just introduced; or whether some natural disaster affects its contracted suppliers. It is difficult to develop such applications today because they require extracting and correlating facts from multiple streaming and stored data sources, typically including unstructured data, which is not well supported by BI platforms today. In this paper, we describe SIE-OBI, a system that we are developing to enable the development and execution of such applications. We describe the novel features of this system, including a declarative interface for rapidly developing such applications, and a platform for optimizing and executing the applications. We illustrate its applicability through two use cases.

A typical online Business Intelligence (BI) workload consists of a combination of short, less intensive queries, along with long, resource intensive queries. As such, the longest queries in a typical BI workload may take several orders of magnitude more time to execute, compared with the shortest queries in the workload. This makes it challenging to design a good Mixed Workload Scheduler (MWS). In this paper we first define the design criteria that make a 'good' MWS. We then use these criteria to design rFEED, a MWS that is fair, effective, efficient, and differentiated. We simulate real workloads and compare our rFEED MWS with models of the current best of breed commercial systems. We show that the rFEED MWS works extremely well.

A typical online business intelligence (BI) workload consists of a combination of short, less intensive queries, along with long, resource intensive queries. As such, the longest queries in a typical BI workload may take several orders of magnitude more time to execute, compared with the shortest queries in the workload. This makes it challenging to design a good mixed workload scheduler (MWS). In this paper we first define the design criteria that make a 'good' MWS. We then use these criteria to design rFEED, a MWS that is fair, effective, efficient, and differentiated. We simulate real workloads and compare our rFEED MWS with models of the current best of breed commercial systems. We show that the rFEED MWS works extremely well.

Modern enterprise data warehouses have complex workloads that are notoriously difficult to manage. An important problem in workload management is to run these complex workloads 'optimally'. Traditionally this problem has been studied in the OLTP (Online Transaction Processing) context where MPL (Multi Programming Level) is used as a knob to achieve optimality. However, MPL is a tricky knob in a BI (Business Intelligence) scenario, since a low MPL can easily result in underload and a high MPL can easily result in overload and 'thrashing'.In this work we present BI Batch Manager, a workload management system to run batches of queries 'optimally' on an Enterprise Data Warehouse (EDW). It is comprised of three components: an admission control component, a scheduler and an execution control component. In order to automatically avoid underload and overload, we introduce a novel execution control mechanism, PGM (Priority Gradient Multiprogramming). In PGM, a priority gradient is created for the workload, with each query running at a distinctly different priority level. We demonstrate that this stabilizes the execution of a workload across a wide operating range. We use memory as the controlling factor for our admission control policy -- admitting batches of queries such that their memory requirement equals the available memory on the system. Our scheduling policy of largest memory query as the highest priority query further stabilizes the execution.We validate our BI Batch Manager using varying workloads on a commercial, enterprise class DBMS. We show that it effectively avoids underload and overload (thrashing) and can automatically run BI workloads with 'optimal' performance.

In this paper we introduce a new single pass clustering algorithm called GenIc designed with the objective of having low overall cost. We examine some of the properties of GenIc and compare it to windowed k-means. We also study its performance using experimental data sets obtained from network monitoring.