Applications

Emotion recognition with EMG data and sensors

Time-series forecasting to fill missing data in an IoT environments

Anomaly detection in sensor data

AES128 encryption in IoT devices with RTOS criteria

Abstract: Human-computer interaction plays a fundamental role in training machine learning models since computers can learn from human behavior. Therefore, this task can be done by cameras and sensors. However, in some scenarios, cameras need a controlled environment to take good-quality pictures and extract patterns from the muscles of the face. Consequently, sensors are a flexible solution in rough applications when humans constantly move or their emotions have weak muscle contractions. In this IoT application,  electromyography sensors are allocated to the human face to recognize the six primary emotions: happiness, anger, surprise, fear, sadness, and disgust. 

 

Resources: Emotion recognition with EMG data

Abstract: Most machine learning (ML) proposals in the Internet of Things (IoT) space are designed and evaluated on pre-processed datasets, where the data acquisition and cleaning steps are often considered a black box. We propose to carry out such techniques not in the cloud servers and closer to the data source, on the IoT device itself. Consequently, this application defines three anomaly detection steps using smoothing filters, unsupervised learning, and deep learning techniques (hybrid model) to detect the different variations of anomalies, focusing on a small computational/memory footprint.

 

Resources: Anomaly detection in sensor data

Abstract:

 

Resources:

Abstract: Internet of Things (IoT) devices have been deployed in different industrial applications due to their feasible implementation. However, they usually work in unpredictable environments, which can affect the communication channel and sensors’ functionalities, which could cause the loss of information.

 

Resources: Time-series forecasting in IoT sensor data