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

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

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

Our AI Research Contributing to NASA’s Artemis Space Program

/in /by

By 2024, the spacecraft “Orion” developed by Lockheed Martin will bring humans to the moon in NASA’s Artemis program. The system invariant analysis technology, one of NEC’s Artificial Intelligence technologies, will perform checks to ensure that the spacecraft is tested and operating properly during the production phase.

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

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

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

Check out our Computervision Papers at #CVPR2022

/in /by

The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) is the premier annual computer vision event comprising the main conference and several co-located workshops and short courses. NEC Laboratories Media Analytics department is excited to be presenting at CVPR 2022, being held in New Orleans, LA from Sunday, June 19 to Friday, June 24, 2022.

Read more

Towards Learning Disentangled Representations for Time Series

/in /by

Promising progress has been made toward learning efficient time series representations in recent years, but the learned representations often lack interpretability and do not encode semantic meanings by the complex interactions of many latent factors. Learning representations that disentangle these latent factors can bring semantic-rich representations of time series and further enhance interpretability. However, directly adopting the sequential models, such as Long Short-Term Memory Variational AutoEncoder (LSTM-VAE), would encounter a Kullback?Leibler (KL) vanishing problem: the LSTM decoder often generates sequential data without efficiently using latent representations, and the latent spaces sometimes could even be independent of the observation space. And traditional disentanglement methods may intensify the trend of KL vanishing along with the disentanglement process, because they tend to penalize the mutual information between the latent space and the observations. In this paper, we propose Disentangle Time-Series, a novel disentanglement enhancement framework for time series data. Our framework achieves multi-level disentanglement by covering both individual latent factors and group semantic segments. We propose augmenting the original VAE objective by decomposing the evidence lower-bound and extracting evidence linking factorial representations to disentanglement. Additionally, we introduce a mutual information maximization term between the observation space to the latent space to alleviate the KL vanishing problem while preserving the disentanglement property. Experimental results on five real-world IoT datasets demonstrate that the representations learned by DTS achieve superior performance in various tasks with better interpretability.

Read more

CAT: Beyond Efficient Transformer for Content-Aware Anomaly Detection in Event Sequences

/in /by

It is critical and important to detect anomalies in event sequences, which becomes widely available in many application domains. Indeed, various efforts have been made to capture abnormal patterns from event sequences through sequential pattern analysis or event representation learning. However, existing approaches usually ignore the semantic information of event content. To this end, in this paper, we propose a self-attentive encoder-decoder transformer framework, Content-Aware Transformer CAT, for anomaly detection in event sequences. In CAT, the encoder learns preamble event sequence representations with content awareness, and the decoder embeds sequences under detection into a latent space, where anomalies are distinguishable. Specifically, the event content is first fed to a content-awareness layer, generating representations of each event. The encoder accepts preamble event representation sequence, generating feature maps. In the decoder, an additional token is added at the beginning of the sequence under detection, denoting the sequence status. A one-class objective together with sequence reconstruction loss is collectively applied to train our framework under the label efficiency scheme. Furthermore, CAT is optimized under a scalable and efficient setting. Finally, extensive experiments on three real-world datasets demonstrate the superiority of CAT.

Read more