Inducing Vascular Grammars for Anomaly Classification in Brain Angiograms

As machine learning is used to make strides in med- ical diagnostics, few methods provide heuristics from which human doctors can learn directly. This work introduces a method for leveraging human observable structures, such as macro scale vascular formations, for producing assessments of medical conditions with rela- tively few training cases, and uncovering patterns that are potential diagnostic aids. The approach draws on shape grammars, a rule-based technique, pioneered in design and architecture, and accelerated through a re- cursive sub-graph mining algorithm. The distribution of rule instances in the data from which they are in- duced is then used as an intermediary representation en- abling common classification and anomaly detection ap- proaches to identify indicative rules with relatively small data sets. The method is applied to 7 Tesla time-of- flight (TOF) angiography MRI (n = 54) of human brain vasculature. The data were segmented and induced to generate representative grammar rules. Ensembles of rules were isolated to implicate vascular conditions reli- ably. This application demonstrates the power of auto- mated structured intermediary representations for as- sessing nuanced biological form relationships, and the strength of shape grammars, in particular for identify- ing indicative patterns in complex vascular networks.

Data-driven and model-based framework for smart water grid anomaly detection and localization

With increasing adoption of advanced meter infrastructure, smart sensors together with SCADA systems, it is imperative to develop novel data analytics and couple the results with hydraulic modeling to improve the quality and efficiency of water services. One important task is to timely detect and localize anomaly events, which may include, but not be limited to, pipe bursts and unauthorized water usages. In this paper, a comprehensive solution framework has been developed for anomaly detection and localization by formulating and integrating data-driven analytics with hydraulic model calibration. Data analysis for anomaly detection proceeds in multiple steps including the following: (1) data pre-processing to eliminate and correct erroneous data records, (2) outlier detection by statistical process control methods and deep machine learning, and (3) system anomaly classification by correlation analysis of multiple sensor events. Classified system anomaly events are subsequently localized via hydraulic model calibration. The integrated solution framework is developed as a user-friendly and effective software tool, tested, and validated on the selected target areas in Singapore.

Model-driven Per-panel Solar Anomaly Detection for Residential Arrays

There has been significant growth in both utility-scale and residential-scale solar installations in recent years, driven by rapid technology improvements and falling prices. Unlike utility-scale solar farms that are professionally managed and maintained, smaller residential-scale installations often lack sensing and instrumentation for performance monitoring and fault detection. As a result, faults may go undetected for long periods of time, resulting in generation and revenue losses for the homeowner. In this article, we present SunDown, a sensorless approach designed to detect per-panel faults in residential solar arrays. SunDown does not require any new sensors for its fault detection and instead uses a model-driven approach that leverages correlations between the power produced by adjacent panels to detect deviations from expected behavior. SunDown can handle concurrent faults in multiple panels and perform anomaly classification to determine probable causes. Using two years of solar generation data from a real home and a manually generated dataset of multiple solar faults, we show that SunDown has a Mean Absolute Percentage Error of 2.98% when predicting per-panel output. Our results show that SunDown is able to detect and classify faults, including from snow cover, leaves and debris, and electrical failures with 99.13% accuracy, and can detect multiple concurrent faults with 97.2% accuracy.

Transfer Learning Strategies for Anomaly Detection in IoT Vibration Data

<div>Abstract—An increasing number of industrial assets are equipped with IoT sensor platforms and the industry now expects data-driven maintenance strategies with minimal deployment costs. However, gathering labeled training data for supervised tasks such as anomaly detection is costly and often difficult to implement in operational environments. Therefore, this work aims to design and implement a solution that reduces the required amount of data for training anomaly classification models on time series sensor data and thereby brings down the overall deployment effort of IoT anomaly detection sensors. We set up several in-lab experiments using three peristaltic pumps and investigated approaches for transferring trained anomaly detection models across assets of the same type. Our experiments achieved promising effectiveness and provide initial evidence that transfer learning could be a suitable strategy for using pretrained anomaly classification models across industrial assets of the same type with minimal prior labeling and training effort. This work could serve as a starting point for more general, pretrained sensor data embeddings, applicable to a wide range of assets.</div>

Transfer Learning Strategies for Anomaly Detection in IoT Vibration Data

<div>Abstract—An increasing number of industrial assets are equipped with IoT sensor platforms and the industry now expects data-driven maintenance strategies with minimal deployment costs. However, gathering labeled training data for supervised tasks such as anomaly detection is costly and often difficult to implement in operational environments. Therefore, this work aims to design and implement a solution that reduces the required amount of data for training anomaly classification models on time series sensor data and thereby brings down the overall deployment effort of IoT anomaly detection sensors. We set up several in-lab experiments using three peristaltic pumps and investigated approaches for transferring trained anomaly detection models across assets of the same type. Our experiments achieved promising effectiveness and provide initial evidence that transfer learning could be a suitable strategy for using pretrained anomaly classification models across industrial assets of the same type with minimal prior labeling and training effort. This work could serve as a starting point for more general, pretrained sensor data embeddings, applicable to a wide range of assets.</div>

Anomaly Detection in Blockchain-enabled Supply Chain: An Ontological Approach

In our proposed work, we propose an anomaly detection framework, for detecting anomalous transactions in business processes from transaction event logs. Such a framework will help enhance the accuracy of anomaly detection in the global Supply Chain, improve the multi-level business processes workflow in the Supply Chain domain, and will optimize the processes in the Supply Chain in terms of security and automation. In the proposed work Ontology is utilized to provide anomaly classification in business transactions, based on crafted SWRL rules for that purpose. Our work has been evaluated based on logs generated from simulating a generic business process model related to a procurement scenario, and the findings show that our framework can detect and classify anomalous transactions form those logs.