Several critical applications, especially in the Internet of Things (IoT) domain, require real-time analysis and predictions based on sensor data. For example, wrist bands attempt to recognize gestures or activities, such as walking or climbing, from inertial measurement unit (IMU) sensor data. Similarly, several audio applications require the detection of specific keywords like "up," "down," or certain urban sounds.

Such applications, especially in the IoT domain, require the deployment of inference on tiny edge devices with capabilities comparable to an Arduino Uno or a Raspberry Pi. Computational intelligence (CI) plays a major role in developing successful intelligent systems, with its coherent formal theory and rambunctious experimental wing. In recent years, there has been an explosion of research on deep learning, which has become the core method for sequential data analysis. Unfortunately, existing state-of-the-art deep learning solutions like the ones based on standard recurrent neural networks or convolutional neural network models are difficult to deploy on tiny devices as they are computationally expensive.

This Special Issue aims to investigate lightweight computational intelligence technologies for sequential data analysis on tiny edge devices. This Special Issue focuses on the problems of fast and efficient processing and analysis of sequential data on tiny edge devices, which is critical for various IoT related applications, including audio keyword detection, gesture identification, video analysis, anomaly detection, and disease prediction. We welcome both original research and review articles.

Potential topics include but are not limited to the following:

• Lightweight machine learning algorithms for sequential data analysis
• Lightweight deep learning algorithms for sequential data analysis
• Life-long learning for sequential data analysis on tiny devices
• Concept drifting of sequential data
• Security and privacy of sequential data in cloud and edge computing
• Evolutional deep learning for sequential data processing
• Lightweight classification and prediction models for time series data
• Sequential data automation, optimization, and transmission in edge computing
• Few-shot learning for data stream analysis
• Micro-service management for data streams
• Distributed computing intelligence in mobile edge computing
• Security and privacy in mobile edge computing
• Advanced computational science and neuroscience algorithms for image stream or video analysis