Dear Colleagues,

Machines are increasingly being given the intelligence to perform more complex tasks, but they remain poor at capturing human emotions. Although both sense and emotion are very important for machine automation, the techniques that have been developed for the latter lag far behind the former. This is because existing emotion recognition methods are insufficiently accurate for real-world use—a serious problem for tasks that require human–machine interaction.

As sensing and artificial intelligence technologies advance, machines are interacting increasingly naturally with humans, recognising human emotions by analysing multiple sensing modes, such as vocalisations and facial expressions. However, machines remain poor at understanding human emotions in real-world uncontrolled conditions due to the gap between laboratory and real-world wild environments. Existing emotionally intelligent robots can recognise simple emotions (contentment, joy, sadness and anger) by interpreting facial expressions and tone of voice, but often fail to intelligently recognise and respond to human emotions. The most important emotion measurement instrument, facial expression analysis, is extremely challenging due to subtle and transient movements in the foreground (people) and complex, noisy environments in the background. That is, in the real world, spontaneous human facial expressions may not be captured in an ideal way; for example, faces may be shown obliquely, at a distance and poorly lit, as opposed to a close-up frontal view with high-quality illumination.

Intelligent emotion recognition methods that are able to tackle the challenges in real-world wild scenarios involving varying head poses, illumination quality and subjects will have a wide range of applications, such as for home-care and business robots. This Special Issue seeks original technical and review papers about the latest technologies for vastly improving machine emotional intelligence in human–machine interaction, including but not limited to machine emotional intelligence for robotics, facial expression recognition in uncontrolled conditions, multimodal sensor data fusion for emotion recognition, emotional cues in speech/language/music, automatic emotional labelling for videos and user emotional preference prediction.

Dr. Guangyan Huang
Dr. Najmeh Samadiani
Dr. Lianhua Chi
Dr. Chi-Hung Chi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• robotic emotional intelligence
• wild facial expression recognition
• multimodal emotional cues
• emotion sensing
• automatic emotional labelling
• user emotional preference