Fast Re-Trainable Attention Autoencoder for Liquid Sensor Anomaly Detection at the Edge

• URL: http://arxiv.org/abs/2507.03995v1
• Date: Sat, 05 Jul 2025 10:51:58 GMT
• Title: Fast Re-Trainable Attention Autoencoder for Liquid Sensor Anomaly Detection at the Edge
• Abstract summary: A lightweight, edge-deployable pipeline is proposed for detecting sensor anomalies in chemistry and biology laboratories.<n>A custom PCB captures seven sensor channels and streams them over the local network.<n>An Attention-based One-Class Autoencoder reaches a usable state after training on only thirty minutes of normal data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: A lightweight, edge-deployable pipeline is proposed for detecting sensor anomalies in chemistry and biology laboratories. A custom PCB captures seven sensor channels and streams them over the local network. An Attention-based One-Class Autoencoder reaches a usable state after training on only thirty minutes of normal data. Despite the small data set, the model already attains an F1 score of 0.72, a precision of 0.89, and a recall of 0.61 when tested on synthetic micro-anomalies. The trained network is converted into a TensorFlow-Lite binary of about 31 kB and runs on an Advantech ARK-1221L, a fan-less x86 edge device without AVX instructions; end-to-end inference latency stays below two seconds. The entire collect-train-deploy workflow finishes within one hour, which demonstrates that the pipeline adapts quickly whenever a new liquid or sensor is introduced.

Related papers

• SIDE: Sensor Impersonation Detection at the Edge via Sequence Prediction [0.0]
  Some low-cost Internet of Things (IoT) sensor deployments lack device-level source authentication.<n>We present a lightweight approach to sensor impersonation detection in a small proof-of-concept study.
  arXiv  Detail & Related papers  (2026-09-05T21:46:07Z)
• Autonomous Cyber Defense: Real-Time Attack Detection and Mitigation in Software-Defined Networks Using Machine Learning [78.29352305480285]
  In recent intrusions, the interval between initial access and the first lateral movement has been observed to be as short as 27 seconds.<n>This paper presents a closed-loop framework that detects and blocks attacks in software-defined networks without operator involvement.
  arXiv  Detail & Related papers  (2026-08-22T18:38:39Z)
• Moving Like a Human: Ego-Motion-Normalized Temporal Signatures for Real-Time Aerial Person Tracking on Milliwatt-Class Hardware [1.932555230783329]
  Follow-me person tracking must run on the drone itself.<n>EMT-Det is a five-stage system that estimates ego-motion.<n>On a Raspberry Pi Zero 2W the pipeline runs at 31.85 FPS with 0.462 AP25 and 0.714 recall over 1,000 real-world UAV videos.
  arXiv  Detail & Related papers  (2026-07-09T19:30:00Z)
• Two kinds of robustness are not the same: disentangling fault tolerance and low-SNR robustness in multi-domain event detection on real data [0.0]
  Event detection underpins induced-seismicity monitoring for CCS and geothermal operations, distributed acoustic sensing (DAS), and industrial condition monitoring.<n>We assemble a unified binary event-detection benchmark from three physically distinct real sources.<n>We evaluate a fault-tolerant detector trained with per-sample sensor-dropout against standard detectors.
  arXiv  Detail & Related papers  (2026-06-28T11:14:20Z)
• Benchmarking IoT Time-Series AD with Event-Level Augmentations [34.864214444544565]
  We introduce an evaluation protocol with unified event-level augmentations that simulate real-world issues.<n>We evaluate 14 representative models on five public anomaly datasets.
  arXiv  Detail & Related papers  (2026-02-17T09:45:44Z)
• MeanFlow Transformers with Representation Autoencoders [71.45823902973349]
  MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data.<n>We develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE)<n>We achieve a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256.
  arXiv  Detail & Related papers  (2025-11-17T06:17:08Z)
• Identification of Capture Phases in Nanopore Protein Sequencing Data Using a Deep Learning Model [0.0]
  We develop a lightweight one-dimensional convolutional neural network (1D CNN) to detect capture phases in down-sampled signal windows.<n>Our best model, CaptureNet-Deep, achieved an F1 score of 0.94 and precision of 93.39% on held-out test data.<n>These results show that efficient, real-time capture detection is possible using simple, interpretable architectures.
  arXiv  Detail & Related papers  (2025-11-03T06:51:53Z)
• TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML [0.0]
  TCUQ is a single pass, label free uncertainty monitor for streaming TinyML.<n>It converts short horizon temporal consistency captured via lightweight signals on posteriors.<n>A streaming conformal layer turns this score into a budgeted accept/abstain rule.
  arXiv  Detail & Related papers  (2025-08-18T13:12:14Z)
• Tiny-HR: Towards an interpretable machine learning pipeline for heart rate estimation on edge devices [6.59529078336196]
  This paper is a proof of concept, machine learning (ML) pipeline that extracts heart rate from pressure sensor data acquired on low-power edge devices. The pipeline consists an upsampler neural network, a signal quality classifier, and a 1D-convolutional neural network optimized for efficient and accurate heart rate estimation. The results indicate that the proposed ML and hybrid pipeline reduces energy and time per inference by 82% and 28% compared to traditional algorithms.
  arXiv  Detail & Related papers  (2022-08-16T22:38:10Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)
• Real-Time Wearable Gait Phase Segmentation For Running And Walking [1.8525902437585904]
  Previous gait phase detection as convolutional neural network (CNN) based classification task requires cumbersome manual setting of time delay or heavy overlapped sliding windows to accurately classify each phase under different test cases. This paper presents a segmentation based gait phase detection with only a single six-axis IMU sensor, which can easily adapt to both walking and running at various speeds. The proposed model on the 20Hz sampling rate data can achieve average error of 8.86 ms in swing time, 9.12 ms in stance time and 96.44% accuracy of gait phase detection and 99.97% accuracy of stride detection
  arXiv  Detail & Related papers  (2022-05-10T04:43:34Z)
• Real Time On Sensor Gait Phase Detection with 0.5KB Deep Learning Model [2.79329087573672]
  Gait phase detection with convolution neural network provides accurate classification but demands high computational cost. This paper presents a segmentation based gait phase detection with a width and depth downscaled U-Net like model that only needs 0.5KB model size and 67K operations per second with 95.9% accuracy.
  arXiv  Detail & Related papers  (2022-05-02T09:59:56Z)
• Low Latency Real-Time Seizure Detection Using Transfer Deep Learning [0.0]
  Scalp electroencephalogram (EEG) signals inherently have a low signal-to-noise ratio. Most popular approaches to seizure detection using deep learning do not jointly model this information or require multiple passes over the signal. In this paper, we exploit both simultaneously by converting the multichannel signal to a grayscale image and using transfer learning to achieve high performance.
  arXiv  Detail & Related papers  (2022-02-16T00:03:00Z)
• Pixel Difference Networks for Efficient Edge Detection [71.03915957914532]
  We propose a lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue datasets are provided to demonstrate its effectiveness. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS.
  arXiv  Detail & Related papers  (2021-08-16T10:42:59Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• Real-time detection of uncalibrated sensors using Neural Networks [62.997667081978825]
  An online machine-learning based uncalibration detector for temperature, humidity and pressure sensors was developed. The solution integrates an Artificial Neural Network as main component which learns from the behavior of the sensors under calibrated conditions. The obtained results show that the proposed solution is able to detect uncalibrations for deviation values of 0.25 degrees, 1% RH and 1.5 Pa, respectively.
  arXiv  Detail & Related papers  (2021-02-02T15:44:39Z)
• Supervised Neural Networks for RFI Flagging [0.0]
  Two machine learning approachesfor flagging real measurement data are demonstrated usingthe existing RFI flagging technique AOFlagger as a groundtruth. This method was able to predict aBoolean flag map for each baseline to a high degree of accuracy achieving a Recall of 0.69 and Precision of 0.83 and anF1-Score of 0.75.
  arXiv  Detail & Related papers  (2020-07-29T06:57:36Z)
• Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications [71.1911136637719]
  We show how provable guarantees can be naturally applied to other real world settings. We show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges.
  arXiv  Detail & Related papers  (2020-06-30T23:33:17Z)
• Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection [99.94079901071163]
  This paper presents a novel end-to-end system for pedestrian detection using Dynamic Vision Sensors (DVSs) We target applications where multiple sensors transmit data to a local processing unit, which executes a detection algorithm. Our detector is able to perform a detection every 450 ms, with an overall testing F1 score of 83%.
  arXiv  Detail & Related papers  (2020-04-03T17:36:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.