Special Issue on Neural Networks and Learning Systems for Human Machine Interfacing
• 大类 : 工程技术 - 2区
• 小类 : 计算机：人工智能 - 3区
As connections between human and machines, the human-machine interfaces (HMI) can process, interpret, recognize and simulate the intention and behaviors of human beings, and then demonstrate intelligent algorithms to drive the machine devices. With developments of sensing and computing technologies, HMIs have been designed to allow mechanical devices to perform complicate tasks intelligently in an unstructured environment by exploring human effects and intentions. Particularly, the HMI is promising to bring humanistic intelligence in robotics devices, biometric systems and other advanced machines by using learning algorithms such as deep neural network. A growing number of researchers and studies focusing on this area in recent years have clearly demonstrated the importance of learning systems for HMI.
Generally, the HMI can include three aspects, i.e., sensing, recognition and control. Sensing is the fundamental of the cognition, perception and learning. Recognition is necessary for understanding of inference of various human actions including body postures, gestures, facial expressions, vocal nuances and other physiological signals. Control is important to generate robust and effective commands to drive the mechanical devices. Recently, due to the fast advances in neural networks and learning systems, novel HMI techniques are emerging, e.g., neuro-signal based sensing techniques, deep learning based recognitions, and neural network based control algorithms. Therefore, combination of the sensing, recognition and control as well as novel neural learning algorithms could possibly lead to breakthrough in the delivery of HMI. Moreover, the applications of HMI technology can improve the usability of the various machines, and they are the pivot of human-machine interaction/collaboration, even human-machine sharing.
The list of possible topics includes, but is not limited to:
- Human robot collaboration using neural networks and learning systems
- Human emotion/sound/motion/behavior recognition using deep neural network
- Control design for human-machine interfaces using neural networks and learning systems
- Integration and fusion of multiple sensors using neural networks and learning systems
- Human-computer interfaces design using learning systems
- Human bio-signal processing and recognition using neural networks
- Neural Networks and learning systems for brain-computer interfacing
- Wearable, mobile and ubiquitous health sensing using learning systems
- Human-centered computational sensing using neural networks and learning systems