Surface Mounted Device (SMD) assembly machine manufactures various products on a flexible manufacturing line. An anomaly detection model that can adapt to the various manufacturing environments very fast is required. In this paper, we proposed a fast adaptive anomaly detection model based on a Recurrent Neural Network (RNN) Encoder–Decoder with operating machine sounds. RNN Encoder–Decoder has a structure very similar to Auto-Encoder (AE), but the former has significantly reduced parameters compared to the latter because of its rolled structure. Thus, the RNN Encoder–Decoder only requires a short training process for fast adaptation. The anomaly detection model decides abnormality based on Euclidean distance between generated sequences and observed sequence from machine sounds. Experimental evaluation was conducted on a set of dataset from the SMD assembly machine. Results showed cutting-edge performance with fast adaptation.

ST elevation myocardial infarction (STEMI) is an acute life-threatening disease. It shows a high mortality risk when a patient is not timely treated within the golden time, prompt diagnosis with limited information such as electrocardiogram (ECG) is crucial. However, previous studies among physicians and paramedics have shown that the accuracy of STEMI diagnosis by the ECG is not sufficient. Thus, we propose a detecting algorithm based on a convolutional neural network (CNN) for detecting the STEMI on 12-lead ECG in order to support physicians, especially in an emergency room. We mostly focus on enhancing the detecting performance using a preprocessing technique. First, we reduce the noise of ECG using a notch filter and high-pass filter. We also segment pulses from ECG to focus on the ST segment. We use 96 normal and 179 STEMI records provided by Seoul National University Bundang Hospital (SNUBH) for the experiment. The sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve are increased from 0.685, 0.350, and 0.526 to 0.932, 0.896, and 0.943, respectively, depending on the preprocessing technique. As our result shows, the proposed method is effective to enhance STEIM detecting performance. Also, the proposed algorithm would be expected to help timely and the accurate diagnosis of STEMI in clinical practices.

World Health Organization (WHO) provides the guideline for managing the Particulate Matter (PM) level because when the PM level is higher, it threats the human health. For managing PM level, the procedure for measuring PM value is needed firstly. We use Tapered Element Oscillating Microbalance (TEOM)-based PM measuring sensors because it shows higher cost-effectiveness than Beta Attenuation Monitor (BAM)-based sensor. However, TEOM-based sensor has higher probability of malfunctioning than BAM-based sensor. In this paper, we call the overall malfunction as an anomaly, and we aim to detect anomalies for the maintenance of PM measuring sensors. We propose a novel architecture for solving the above aim that named as Hypothesis Pruning Generative Adversarial Network (HP-GAN). We experimentally compare the several anomaly detection architectures to certify ours performing better.

The World Health Organization provides guidelines for managing the particulate matter (PM) level because a higher PM level represents a threat to human health. To manage the PM level, a procedure for measuring the PM value is first needed. We use a PM sensor that collects the PM level by laser‐based light scattering (LLS) method because it is more cost effective than a beta attenuation monitor‐based sensor or tapered element oscillating microbalance‐based sensor. However, an LLS‐based sensor has a higher probability of malfunctioning than the higher cost sensors. In this paper, we regard the overall malfunctioning, including strange value collection or missing collection data as anomalies, and we aim to detect anomalies for the maintenance of PM measuring sensors. We propose a novel architecture for solving the above aim that we call the hypothesis pruning generative adversarial network (HP‐GAN). Through comparative experiments, we achieve AUROC and AUPRC values of 0.948 and 0.967, respectively, in the detection of anomalies in LLS‐based PM measuring sensors. We conclude that our HP‐GAN is a cutting‐edge model for anomaly detection.

Malignant arrhythmia triggers critical attack on the heart and it can lead cardiac patients to death. We propose an arrhythmia detection algorithm based on recurrent neural network encoder–decoder (RED). Collecting arrhythmia data is practically possible, but it is costly because of arrhythmia has varying types. We ease the cost of labeling for constructing dataset using RED because it can be trained with normal data only. Also, collecting many kinds of arrhythmia data requires lots of cost. Also, for more efficient training, we use the Lyapunov exponent (LE) to extract features from electrocardiography. LE helps training RED with only a few data from normal people. RED determines the arrhythmia according to the restoration error. We assessed our algorithm with the MIT‐BIH Arrhythmia Database with a cutting‐edge performance on arrhythmia detection. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.