Nowadays, there is an exponentially increasing amount of data from cameras, webcams, or other optical or radar sensors. Proper ways of mining and using these data could make great contributions to the development of civil and military technologies. For example, optical and radar images can be employed to detect and recognize the interested targets in a large scene to help intelligence interpretation and battlefield surveillance. Furthermore, the data from the two types of sensors can be properly fused to find more latent information.

However, it is still a challenging problem to develop automatic and intelligent algorithms to process the massive data from different sensors. Recently, the advances in machine learning and scientific programming have shown their potential in practical applications including signal processing, image interpretation, and data fusion. These deep learning and scientific programming algorithms provide general tools for different sources of data including 1D, 2D, 3D, or more high-dimensional ones. In this sense, the machine learning techniques can be properly employed in the field of data processing from multiple sensors.

Therefore, the aim of this Special Issue is to welcome original research and review articles with a focus on applying advanced machine learning and scientific programming approaches in data processing from multiple sensors. The Issue aims to provide novel guidance for machine learning researchers and broaden the perspectives of machine learning and sensor-related researchers.

Potential topics include but are not limited to the following:

• Machine learning in optical image processing
• Machine learning in video processing
• Machine learning in radar signal / image processing
• Machine learning in Internet of Things (IoT)
• Machine learning in multisensor data fusion
• Machine learning in the cooperative working of multiple sensors
• Scientific programming in data fusion
• Scientific programming in data forecasting
• Scientific programming in pattern recognition