No abstract

In this paper, we explore data collected in a pilot project that used a digital camera and facial recognition to detect foot traffic to a sports store. Using a time series approach, we model daily incoming store traffic under three classes (all faces, female, male) and compare six forecasting approaches, including Holt-Winters (HW), a Support Vector Machine (SVM) and a HW-SVM hybrid that includes other data features (e.g., weather conditions). Several experiments were held, under a robust rolling windows scheme that considers up to one week ahead predictions and two metrics (predictive error and estimated store benefit). Overall, competitive results were achieved by the SVM (all faces), HW (female) and HW-SVM (male) methods, which can potentially lead to valuable gains (e.g., enhancing store marketing or human resource management).

No abstract

Recently, there have been advances in using unsupervised learning methods for Acoustic Anomaly Detection (AAD). In this paper, we propose an improved version of two deep AutoEncoders (AE) for unsupervised AAD for six types of working machines, namely Dense and Convolutional AEs. A large set of computational experiments was held, showing that the two proposed deep autoencoders, when combined with a mel-spectrogram sound preprocessing, are quite competitive and outperform a recently proposed AE baseline. Overall, a high-quality class discrimination level was achieved, ranging from 72% to 92%.

Within the context of Industry 4.0, quality assessment procedures using data-driven techniques are becoming more critical due to the generation of massive amounts of production data. In this paper, we address the detection of abnormal screw tightening processes, which is a relevant industrial task. Since labeling is costly, requiring a manual effort, we focus on unsupervised approaches. In particular, we assume a low-dimensional input screw fastening approach that is based only on angle-torque pairs. Using such pairs, we explore three main unsupervised Machine Learning (ML) algorithms: Local Outlier Factor (LOF), Isolation Forest (iForest) and a deep learning Autoencoder (AE). For benchmarking purposes, we also explore a supervised Random Forest (RF) algorithm. Several computational experiments were held by using recent industrial data with 2.8 million angle-torque pair records and a realistic and robust rolling window evaluation. Overall, high quality anomaly discrimination results were achieved by the iForest (99%) and AE (95% and 96%) unsupervised methods, which compared well against the supervised RF (99% and 91%). When compared with iForest, the AE requires less computation effort and provides faster anomaly detection response times.