Activity recognition is considered as an important task in many applications, particularly in healthcare services. Among these applications include medical diagnostic, monitoring of users' daily routine and detection of abnormal cases. This paper presents an approach for the activity recognition using an accelerometer sensor embedded in a smartphone. This approach uses a publicly available accelerometer dataset as the raw input signal. The features of the signal are selected based on the time and frequency domain. Then, Principal Component Analysis (PCA) is used to reduce the dimensionality of the features and extract the most significant ones that can classify human activities. A comparison process is performed between the original raw data and PCA-based features and additionally, time and frequency-domain features are also compared using several machine learning classifiers. The obtained results show that the PCA-based features obtain higher recognition rate while frequency-domain features have higher accuracy, with the rate of 96.11% and 92.10% respectively.

This paper presents the development of a real-time cloud-based in-vehicle air quality monitoring system that enables the prediction of the current and future cabin air quality. The designed system provides predictive analytics using machine learning algorithms that can measure the drivers’ drowsiness and fatigue based on the air quality presented in the cabin car. It consists of five sensors that measure the level of CO₂, particulate matter, vehicle speed, temperature, and humidity. Data from these sensors were collected in real-time from the vehicle cabin and stored in the cloud database. A predictive model using multilayer perceptron, support vector regression, and linear regression was developed to analyze the data and predict the future condition of in-vehicle air quality. The performance of these models was evaluated using the Root Mean Square Error, Mean Squared Error, Mean Absolute Error, and coefficient of determination (R²). The results showed that the support vector regression achieved excellent performance with the highest linearity between the predicted and actual data with an R² of 0.9981.

Accurate activity recognition plays a major role in smart homes to provide assistance and support for users, especially elderly and cognitively impaired people. To realize this task, knowledge-driven approaches are one of the emerging research areas that have shown interesting advantages and features. However, several limitations have been associated with these approaches. The produced models are usually incomplete to capture all types of human activities. This resulted in the limited ability to accurately infer users’ activities. This paper presents an alternative approach by combining knowledge-driven with data-driven reasoning to allow activity models to evolve and adapt automatically based on users’ particularities. Firstly, a knowledge-driven reasoning is presented for inferring an initial activity model. The model is then trained using data-driven techniques to produce a dynamic activity model that learns users’ varying action. This approach has been evaluated using a publicly available dataset and the experimental results show the learned activity model yields significantly higher recognition rates compared to the initial activity model.

Device-free localization (DFL) has become a hot topic in the paradigm of the Internet of Things. Traditional localization methods are focused on locating users with attached wearable devices. This involves privacy concerns and physical discomfort especially to users that need to wear and activate those devices daily. DFL makes use of the received signal strength indicator (RSSI) to characterize the user’s location based on their influence on wireless signals. Existing work utilizes statistical features extracted from wireless signals. However, some features may not perform well in different environments. They need to be manually designed for a specific application. Thus, data processing is an important step towards producing robust input data for the classification process. This paper presents experimental procedures using the deep learning approach to automatically learn discriminative features and classify the user’s location. Extensive experiments performed in an indoor laboratory environment demonstrate that the approach can achieve 84.2% accuracy compared to the other basic machine learning algorithms.

In-vehicle air quality monitoring systems have been seen as promising paradigms for monitoring drivers’ conditions while they are driving. This is because some in-vehicle cabins contain pollutants that can cause drowsiness and fatigue to drivers. However, designing an efficient system that can predict in-vehicle air quality has challenges, due to the continuous variation in parameters in cabin environments. This paper presents a new approach, using deep learning techniques that can deal with the varying parameters inside the vehicle environment. In this case, two deep learning models, namely Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) are applied to classify and predict the air quality using time-series data collected from the built-in sensor hardware. Both are compared with conventional methods of machine learning models, including Support Vector Regression (SVR) and Multi-layer Perceptron (MLP). The results show that GRU has an excellent prediction performance with the highest coefficient of determination value (R²) of 0.97.