In this era of artificial intelligence (AI) and big data, the approaches for data analysis, information extraction, and underlying event analysis with state-of-the-art machine learning algorithms have grown radically. Hence, there is an increasing demand for solutions that can successfully handle enormous data from lots of sensors and model the events in data. Assisted systems incorporate systems, applications, and services adopting sensors, measurement methods, and information technologies to offer new products and solutions to address various necessities, such as health and wellbeing. The expected outcomes from the introduction of such a paradigm include a positive impact on health-related quality of life, reducing the costs of healthcare provision at the same time.
Despite the marvelous advancements and achievements of artificial intelligence fields so far, their black-box nature and questions around the lack of transparency are still hampering their applications in society. To trust, accept, and adopt emerging AI solutions in our lives and practices, explainable AI (XAI) is in very much demand these days, along with state-of-the-art machine learning algorithms such as convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), neural structured learning (NSL), etc. XAI can provide human-understandable interpretations by explaining the machine learning model’s algorithmic behavior and outcomes. Thus, it can enable people to control and continuously improve the performance, transparency, and explainability throughout the lifecycle of AI applications. Considering this motivation, the recently emerging trend among the diverse and multidisciplinary research communities is exploration of AI approaches and the development of contextual models.
This Special Issue highlights the recent advances and future trends in developing intelligent and smart wearable and/or ambient sensor-based systems, methods, and frameworks to measure the wellbeing of people. It also focuses on machine learning approaches to model the underlying events in the data. Algorithms related to XAI would be quite interesting and encouraging in this regard, along with other machine learning algorithms to handle distinguished sensor data for assisted systems. We invite manuscripts on a wide range of smart sensing and machine learning research for assisted systems, including but not limited to:
- Artificial intelligence;
- Explainable AI models;
- Human–computer interactions;
- Robotics for healthcare;
- Signal processing;
- Multimodal sensing;
- Feature analysis;
- Context-based sensing;
- Knowledge discovery from sensor data;
- Machine learning on sensor data;
- Data analysis for smart sensing;
- Sensor data applications;
- Pattern recognition;
- Smart-assisted system;
- Expert systems and applications.
Dr. Md Zia Uddin
Dr. Ahmet Soylu