Abstract
Facial expression analysis is a widespread technology applied in various research areas, including sports science. In the last few decades, facial expression analysis has become a key technology for monitoring physical exercise. In this paper, a deep neural network is proposed to recognize seven basic emotions and their corresponding probability values (scores). The score of the neutral emotion was tracked throughout the exercise and related with heart rate and power generation by a stationary bicycle. It was found that in a certain power range, a participant changes his/her expression drastically. Twelve university students participated in the sub-maximal physical exercise in stationary bicycles. A facial video, heart rate,and power generation were recorded throughout the exercise. All the experiments, including the facial expression analysis, were carried out offline. The score of the neutral emotion and its derivative was plotted against maxHR% and maxPower%. The threshold point was determined by calculating the local minima, with the threshold power for all the participants being within 80% to 90% of its maximum value. From the results, it is concluded that the facial expression was different from one individual to another, but it was more consistant with power generation. The threshold point can be a useful cue for various purposes, such as: physiological parameter prediction and automatic load control in the exercise equipment, such as treadmill and stationary bicycle. © 2020, Springer Nature Switzerland AG.

Abstract
Diabetes Mellitus (DM) is one of the most predominant diseases in the world, causing a high number of deaths. Diabetic foot is one of the main complications observed in diabetic patients, which can lead to the development of ulcers. As the risk of ulceration is directly linked to an increase of the temperature in the plantar region, several studies use thermography as a method for automatic identification of problems in diabetic foot. As the distribution of plantar temperature of diabetic patients do not follow a specific pattern, it is difficult to measure temperature changes and, therefore, there is an interest in the development of methods that allow the detection of these abnormal changes. The objective of this work is to develop a methodology that uses thermograms of the feet of diabetic and healthy individuals and analyzes the thermal changes diversity in the plantar region, classifying each foot as belonging to a DM or a healthy individual. Based on the concept of clustering, a binary classifier to predict diabetic foot is presented; both a quantitative indicator and a classification thresholder (evaluated and validated by several performance metrics) are presented. To measure the binary classifier performance, experiments were conducted on a public dataset (with 122 images of DM individuals and 45 of healthy ones), being obtained the following metrics: Sensitivity = 0.73, Fmeasure = 0.81 and AUC = 0.84.

Abstract
Through technological advents from Industry 4.0 and the Internet of Things, as well as new Big Data solutions, predictive maintenance begins to play a strategic role in the increasing operational performance of any industrial facility. Equipment failures can be very costly and have catastrophic consequences. In its basic concept, Predictive maintenance allows minimizing equipment faults or service disruptions, presenting promising cost savings. This paper presents a data-driven approach, based on multiple-instance learning, to predict malfunctions in End-of-Line Testing Systems through the extraction of operational logs, which, while not designed to predict failures, contains valid information regarding their operational mode over time. For the case study performed, a real-life dataset was used containing thousands of log messages, collected in a real automotive industry environment. The insights gained from mining this type of data will be shared in this paper, highlighting the main challenges and benefits, as well as good recommendations, and best practices for the appropriate usage of machine learning techniques and analytics tools that can be implemented in similar industrial environments. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Abstract
Quality automobile inspection is one of the critical application areas to achieve better quality at low cost and can be obtained with the advance computer vision technology. Whether for the quality inspection or the automatic assembly of automobile parts, automatic recognition of automobile parts plays an important role. In this article, vehicle parts are classified using deep neural network architecture designed based on ConvNet. The public dataset available in CompCars [1] were used to train and test a VGG16 deep learning architecture with a fully connected output layer of 8 neurons. The dataset has 20,439 RGB images of eight interior and exterior car parts taken from the front view. The dataset was first separated for training and testing purpose, and again training dataset was divided into training and validation purpose. The average accuracy of 93.75% and highest accuracy of 97.2% of individual parts recognition were obtained. The classification of car parts contributes to various applications, including car manufacturing, model verification, car inspection system, among others. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Abstract
The automotive industry has an extremely high-quality product standard, not just for the security risks each faulty component can present, but the very brand image it must uphold at all times to stay competitive. In this paper, a prototype model is proposed for smart quality inspection using machine vision. The engine labels are detected using Faster-RCNN and YOLOv3 object detection algorithms. All the experiments were carried out using a custom dataset collected at an automotive assembly plant. Eight engine labels of two brands (Citroën and Peugeot) and more than ten models were detected. The results were evaluated using the metrics Intersection of Union (IoU), mean of Average Precision (mAP), Confusion Matrix, Precision and Recall. The results were validated in three folds. The models were trained using a custom dataset containing images and annotation files collected and prepared manually. Data Augmentation techniques were applied to increase the image diversity. The result without data augmentation was 92.5%, and with it the value was up-to 100%. Faster-RCNN has more accurate results compared to YOLOv3. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Abstract
In the competitive automotive market, where extremely high-quality standards must be ensured independently of the growing product and manufacturing complexity brought by customization, reliable and precise detection of any non-conformities before the vehicle leaves the assembly line is paramount. In this paper we propose a wearable solution to aid quality control workers in the detection, visualization and relay of any non-conformities, while also reducing known performance issues such as skill gaps and fatigue, and improving training methods. We also explore how the reliability, precision and validity tests of the visualization module of our framework were performed, guaranteeing a 0% chance occurrence of undesired non-conformities in the following usability tests and training simulator. © 2021, Springer Nature Switzerland AG.