Activity recognition systems are a large field of research and development, currently with a focus on advanced machine learning algorithms, innovations in the field of hardware architecture, and on decreasing the costs of monitoring while increasing safety. This article concentrates on the applications of activity recognition systems and surveys their state of the art. We categorize such applications into active and assisted living systems for smart homes, healthcare monitoring applications, monitoring and surveillance systems for indoor and outdoor activities, and tele-immersion applications. Within these categories, the applications are classified according to the methodology used for recognizing human behavior, namely, based on visual, non-visual, and multimodal sensor technology. We provide an overview of these applications and discuss the advantages and limitations of each approach. Additionally, we illustrate public data sets that are designed for the evaluation of such recognition systems. The article concludes with a comparison of the existing methodologies which, when applied to real-world scenarios, allow to formulate research questions for future approaches.

One of the main objectives of Active and Assisted Living (AAL) environments is to ensure that elderly and/or disabled people perform/live well in their immediate environments; this can be monitored by among others the recognition of emotions based on non-highly intrusive sensors such as Electrodermal Activity (EDA) sensors. However, designing a learning system or building a machine-learning model to recognize human emotions while training the system on a specific group of persons and testing the system on a totally a new group of persons is still a serious challenge in the field, as it is possible that the second testing group of persons may have different emotion patterns. Accordingly, the purpose of this paper is to contribute to the field of human emotion recognition by proposing a Convolutional Neural Network (CNN) architecture which ensures promising robustness-related results for both subject-dependent and subject-independent human emotion recognition. The CNN model has been trained using a grid search technique which is a model hyperparameter optimization technique to fine-tune the parameters of the proposed CNN architecture. The overall concept’s performance is validated and stress-tested by using MAHNOB and DEAP datasets. The results demonstrate a promising robustness improvement regarding various evaluation metrics. We could increase the accuracy for subject-independent classification to 78% and 82% for MAHNOB and DEAP respectively and to 81% and 85% subject-dependent classification for MAHNOB and DEAP respectively (4 classes/labels). The work shows clearly that while using solely the non-intrusive EDA sensors a robust classification of human emotion is possible even without involving additional/other physiological signals.

Emotions play an extremely important role in how we make a decision, planning, reasoning and other human mental states. The recognition of these emotions is becoming a vital task for e-healthcare systems. Using bio-sensors such as Electroencephalogram (EEG) to recognise the mental state of patients that could need a special care offers an important feedback for Ambient Assisted Living (AAL). This paper presents an EEG-based emotion recognition approach to detect the emotional state of patients. The proposed approach combines wavelet energy, modified energy, wavelet entropy and statistical features to classify four emotion states. Three different classifiers are used (quadratic discriminant analysis, k-nearest neighbor, and support vector machines) to recognise the emotion of patients robustly. The new approach is tested based on the EEG database “DEAP” using four electrodes. It shows high performance compared to existing algorithms. An overall classification accuracy of 83.87% is obtained.

Many of the basic image processing tasks suffer from processing overhead to operate over the whole image. In real time applications the processing time is considered as a big obstacle for its implementations. A High Performance Computing (HPC) platform is necessary in order to solve this problem. The usage of hardware accelerator make the processing time low. In recent developments, the Graphics Processing Unit (GPU) is being used in many applications. Along with the hardware accelerator a proper choice of the computing algorithm makes it an added advantage for fast processing of images. The Cellular Neural Network (CNN) is a large-scale nonlinear analog circuit able to process signals in real time [1]. In this paper, we develop a new design in evaluation of image processing algorithms on the massively parallel GPUs with CNN implementation using Open Computing Language (OpenCL) programming model. This implementation uses the Discrete Time CNN (DT-CNN) model which is derived from originally proposed CNN model. The inherent massive parallelism of CNN along with GPUs makes it an advantage for high performance computing platform [2]. The advantage of OpenCL makes the design to be portable on all the available graphics processing devices and multi core processors. Performance evaluation is done in terms of execution time with both device (i.e. GPU) and host (i.e. CPU).

Several intrusive and non-intrusive techniques have been proposed in the past to monitor car driver's emotions but very little light was shed on using thermal cameras for such applications. This paper details with one such system that uses a single infrared thermal camera. Such a camera was used to overcome the issues pertaining to usage of single audio/visual sensors. Fusion of the outputs with the audio/visual sensors could provide a better ADAS (Advanced Driver Assistance System). The paper also details face detection techniques in each thermogram prior to emotion recognition.