Explainable Anomaly Detection System for Categorical Sensor Data in Internet of Things

/in /by

Internet of things (IoT) applications deploy massive number of sensors to monitor the system and environment. Anomaly detection on streaming sensor data is an important task for IoT maintenance and operation. However, there are two major challenges for anomaly detection in real IoT applications: (1) many sensors report categorical values rather than numerical readings, (2) the end users may not understand the detection results, they require additional knowledge and explanations to make decision and take action. Unfortunately, most existing solutions cannot satisfy such requirements. To bridge the gap, we design and develop an eXplainable Anomaly Detection System (XADS) for categorical sensor data. XADS trains models from historical normal data and conducts online monitoring. XADS detects the anomalies in an explainable way: the system not only reports anomalies’ time periods, types, and detailed information, but also provides explanations on why they are abnormal, and what the normal data look like. Such information significantly helps the decision making for users. Moreover, XADS requires limited parameter setting in advance, yields high accuracy on detection results and comes with a user-friendly interface, making it an efficient and effective tool to monitor a wide variety of IoT applications.

Read more

Multi-source Inductive Knowledge Graph Transfer

/in /by

Multi-source Inductive Knowledge Graph Transfer Large-scale information systems, such as knowledge graphs (KGs), enterprise system networks, often exhibit dynamic and complex activities. Recent research has shown that formalizing these information systems as graphs can effectively characterize the entities (nodes) and their relationships (edges). Transferring knowledge from existing well-curated source graphs can help construct the target graph of newly-deployed systems faster and better which no doubt will benefit downstream tasks such as link prediction and anomaly detection for new systems. However, current graph transferring methods are either based on a single source, which does not sufficiently consider multiple available sources, or not selectively learns from these sources. In this paper, we propose MSGT-GNN, a graph knowledge transfer model for efficient graph link prediction from multiple source graphs. MSGT-GNN consists of two components: the Intra-Graph Encoder, which embeds latent graph features of system entities into vectors, and the graph transferor, which utilizes graph attention mechanism to learn and optimize the embeddings of corresponding entities from multiple source graphs, in both node level and graph level. Experimental results on multiple real-world datasets from various domains show that MSGT-GNN outperforms other baseline approaches in the link prediction and demonstrate the merit of attentive graph knowledge transfer and the effectiveness of MSGT-GNN.

Read more

Simultaneous Sensing and Communication in Optical Fibers

/in /by

We explore two fiber sensing methods which enables coexistence with data transmission on DWDM fiber networks. Vibration detection and localization can be achieved by extracting optical phase from modified coherent transponders. Frequency-diverse chirped-pulse DAS with all-Raman amplification can improve SNR and achieves multi-span monitoring.

Read more

DataXc: Flexible and efficient communication in microservices-based stream analytics pipelines

/in /by

A big challenge in changing a monolithic application into a performant microservices-based application is the design of efficient mechanisms for microservices to communicate with each other. Prior proposals range from custom point-to-point communication among microservices using protocols like gRPC to service meshes like Linkerd to a flexible, many-to-many communication using broker-based messaging systems like NATS. We propose a new communication mechanism, DataXc, that is more efficient than prior proposals in terms of message latency, jitter, message processing rate and use of network resources. To the best of our knowledge, DataXc is the first communication design that has the desirable flexibility of a broker-based messaging systems like NATS and the high-performance of a rigid, custom point-to-point communication method. DataXc proposes a novel “pull” based communication method (i.e consumers fetch messages from producers). This is unlike prior proposals like NATS, gRPC or Linkerd, all of which are “push” based (i.e. producers send messages to consumers). Such communication methods make it difficult to take advantage of differential processing rates of consumers like video analytics tasks. In contrast, DataXc proposes a “pull” based design that avoids unnecessary communication of messages that are eventually discarded by the consumers. Also, unlike prior proposals, DataXc successfully addresses several key challenges in streaming video analytics pipelines like non-uniform processing of frames from multiple cameras, and high variance in latency of frames processed by consumers, all of which adversely affect the quality of insights from streaming video analytics. We report results on two popular real-world, streaming video analytics pipelines (video surveillance, and video action recognition). Compared to NATS, DataXc is just as flexible, but it has far superior performance: upto 80% higher processing rate, 3X lower latency, 7.5X lower jitter and 4.5X lower network bandwidth usage. Compared to gRPC or Linkerd, DataXc is highly flexible, achieves up to 2X higher processing rate, lower latency and lower jitter, but it also consumes more network bandwidth.

Read more

3D Histogram-Based Anomaly Detection for Categorical Sensor Data in Internet of Things

/in /by

The applications of Internet-of-things (IoT) deploy a massive number of sensors to monitor the system and environment. Anomaly detection on streaming sensor data is an important task for IoT maintenance and operation. In real IoT applications, many sensors report categorical values rather than numerical readings. Unfortunately, most existing anomaly detection methods are designed only for numerical sensor data. They cannot be used to monitor the categorical sensor data. In this study, we design and develop a 3D Histogram-based Categorical Anomaly Detection (HCAD) solution to monitor categorical sensor data in IoT. HCAD constructs the histogram model by three dimensions: categorical value, event duration, and frequency. The histogram models are used to profile normal working states of IoT devices. HCAD automatically determines the range of normal data and anomaly threshold. It only requires very limited parameter setting and can be applied to a wide variety of different IoT devices. We implement HCAD and integrate it into an online monitoring system. We test the proposed solution on real IoT datasets such as telemetry data from satellite sensors, air quality data from chemical sensors, and transportation data from traffic sensors. The results of extensive experiments show that HCAD achieves higher detecting accuracy and efficiency than state-of-the-art methods.

Read more

Finite Element Modeling of Pavement and State Awareness Using Fiber Optic Sensing

/in /by

A variety of efforts have been put into sensing and modeling of pavements. Such capability is commonly validated with experimental data and used as reference for damage detection and other structural changes. Finite element models (FEM) often provides a high fidelity physics-base benchmark to evaluate the pavement integrity. On the monitoring of roads and pavements in general, FEM combining with in-situ data largely extends the awareness of the pavement condition, and enhances the durability and sustainability for the transportation infrastructures. Although many studies were performed in order to simulate static stress and strain in the pavement, FEM also show potential for dynamic analysis, allowing to extract both frequency response and wave propagation at any location, including the behavior of the soil on the surroundings. Fiber optical sensing is adopted in this research, which outperforms the traditional sensing techniques, such as accelerometers or strain gauges, given its nature of providing continuous measurement in a relatively less intrinsic fashion. Moreover, the data is adopted to validate and calibrate the FEM with complex material properties, such as damping and viscoelasticity of the pavement as well as other nonlinear behavior of the surrounded soil. The results demonstrate a successful FEM with good accuracy of the waveform prediction.

Read more

Vibration-Based Status Identification of Power Transmission Poles

/in /by

Among the power transmission infrastructures, the low-voltage overhead power lines are specifically critical, due to the complicated roadside environments and the significant number of connections to the end utility users. Maintaining of such a large size grid with mostly wood poles is a challenging task and knowing the operating status and its structural integrity drastically speeds up the routine inspection. Applying a data-driven approach using accelerometer data to analyze the power line-induced vibration to classify different poles within different operational conditions is proposed.Feature creation is the important aspect to improve an accuracy of data-driven algorithms. For this purpose, a time-frequency domain classifier is developed, based on the data collected from two tri-axial accelerometers installed on the wood poles before and after streetlights are on. Data are explored both in time and frequency domain using techniques such as data augmentation and segmentation, averaging, filtering, and principal component analysis. Results of the machine learning classifier clearly shows distinct characteristics among the data collected from different work conditions and different poles. Further exploration of the applied algorithm will be pursued to construct more sophisticated features based on supervised learning to enhance the identification accuracy.

Read more

RoVaR: Robust Multi-agent Tracking through Dual-layer Diversity in Visual and RF Sensor Fusion

/in /by

The plethora of sensors in our commodity devices provides a rich substrate for sensor-fused tracking. Yet, today’s solutions are unable to deliver robust and high tracking accuracies across multiple agents in practical, everyday environments – a feature central to the future of immersive and collaborative applications. This can be attributed to the limited scope of diversity leveraged by these fusion solutions, preventing them from catering to the multiple dimensions of accuracy, robustness (diverse environmental conditions) and scalability (multiple agents) simultaneously.In this work, we take an important step towards this goal by introducing the notion of dual-layer diversity to the problem of sensor fusion in multi-agent tracking. We demonstrate that the fusion of complementary tracking modalities, – passive/relative (e.g. visual odometry) and active/absolute tracking (e.g.infrastructure-assisted RF localization) offer a key first layer of diversity that brings scalability while the second layer of diversity lies in the methodology of fusion, where we bring together the complementary strengths of algorithmic (for robustness) and data-driven (for accuracy) approaches. ROVAR is an embodiment of such a dual-layer diversity approach that intelligently attends to cross-modal information using algorithmic and data-driven techniques that jointly share the burden of accurately tracking multiple agents in the wild. Extensive evaluations reveal ROVAR’S multi-dimensional benefits in terms of tracking accuracy, scalability and robustness to enable practical multi-agent immersive applications in everyday environments.

Read more

Application-specific, Dynamic Reservation of 5G Compute and Network Resources by using Reinforcement Learning

/in /by

5G services and applications explicitly reserve compute and network resources in today’s complex and dynamic infrastructure of multi-tiered computing and cellular networking to ensure application-specific service quality metrics, and the infrastructure providers charge the 5G services for the resources reserved. A static, one-time reservation of resources at service deployment typically results in extended periods of under-utilization of reserved resources during the lifetime of the service operation. This is due to a plethora of reasons like changes in content from the IoT sensors (for example, change in number of people in the field of view of a camera) or a change in the environmental conditions around the IoT sensors (for example, time of the day, rain or fog can affect data acquisition by sensors). Under-utilization of a specific resource like compute can also be due to temporary inadequate availability of another resource like the network bandwidth in a dynamic 5G infrastructure. We propose a novel Reinforcement Learning-based online method to dynamically adjust an application’s compute and network resource reservations to minimize under-utilization of requested resources, while ensuring acceptable service quality metrics. We observe that a complex application-specific coupling exists between the compute and network usage of an application. Our proposed method learns this coupling during the operation of the service, and dynamically modulates the compute and network resource requests to mimimize under-utilization of reserved resources. Through experimental evaluation using real-world video analytics application, we show that our technique is able to capture complex compute-network coupling relationship in an online manner i.e. while the application is running, and dynamically adapts and saves up to 65% compute and 93% network resources on average (over multiple runs), without significantly impacting application accuracy.

Read more

Cosine Similarity based Few-Shot Video Classifier with Attention-based Aggregation

/in /by

Meta learning algorithms for few-shot video recognition use complex, episodic training but they often fail to learn effective feature representations. In contrast, we propose a new and simpler few-shot video recognition method that does not use meta-learning, but its performance compares well with the best meta-learning proposals. Our new few-shot video classification pipeline consists of two distinct phases. In the pre-training phase, we learn a good video feature extraction network that generates a feature vector for each video. After a sparse sampling strategy selects frames from the video, we generate a video feature vector from the sampled frames. Our proposed video feature extractor network, which consists of an image feature extraction network followed by a new transformer encoder, is trained end-to-end by including a classifier head that uses cosine similarity layer instead of the traditional linear layer to classify a corpus of labeled video examples. Unlike prior work in meta learning, we do not use episodic training to learn the image feature vector. Also, unlike prior work that averages frame-level feature vectors into a single video feature vector, we combine individual frame-level feature vectors by using a new Transformer encoder that explicitly captures the key, temporal properties in the sequence of sampled frames. End-to-end training of the video feature extractor ensures that the proposed Transformer encoder captures important temporal properties in the video, while the cosine similarity layer explicitly reduces the intra-class variance of videos that belong to the same class. Next, in the few-shot adaptation phase, we use the learned video feature extractor to train a new video classifier by using the few available examples from novel classes. Results on SSV2-100 and Kinetics-100 benchmarks show that our proposed few-shot video classifier outperforms the meta-learning-based methods and achieves the best state-of-the-art accuracy. We also show that our method can easily discern between actions and their inverse (for example, picking something up vs. putting something down), while prior art, which averages image feature vectors, is unable to do so.

Read more