A Multilayer Perceptron (MLP) is a class of feedforward artificial neural network composed of an input layer, one or more fully connected hidden layers with nonlinear activation functions, and an output layer, enabling the learning of complex nonlinear mappings from input features to output predictions. In CSI-based Wi-Fi sensing, MLPs are commonly employed as classification or regression backends that take handcrafted or learned CSI feature representations as input to perform tasks such as activity recognition, gesture detection, and crowd counting, making them a fundamental baseline and building block in the field. Key variants include shallow single-hidden-layer perceptrons used for lightweight deployment, deeper stacked architectures that increase representational capacity, and hybrid models where an MLP serves as the decision head atop convolutional or recurrent feature extractors, with the choice of depth and width directly influencing generalization across heterogeneous environments.
Source Papers
- A survey on CSI-based Wi-Fi sensing datasets and models with a focus on reproducibility ↗ — A survey on CSI-based Wi-Fi sensing datasets and models with
- CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing ↗ — CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing
- Data Assimilation for Agent-Based Models ↗ — Data Assimilation for Agent-Based Models
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- Human Activity Recognition via Wi-Fi and Inertial Sensors With Machine Learning ↗ — Human Activity Recognition via Wi-Fi and Inertial Sensors Wi
- Investigation of Environment Dependence in Wi-Fi CSI-Based Crowd Counting Systems ↗ — Investigation of Environment Dependence in Wi-Fi CSI-Based C
- NeRF2: Neural Radio-Frequency Radiance Fields ↗ — NeRF2: Neural Radio-Frequency Radiance Fields
- Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions ↗ — Occupancy Prediction in IoT-Enabled Smart Buildings: Technol
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing ↗ — SenseFi: A library and benchmark on deep-learning-empowered
- WiFi-Based Human Sensing With Deep Learning: Recent Advances, Challenges, and Opportunities ↗ — WiFi-Based Human Sensing With Deep Learning: Recent Advances
- WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing ↗ — WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activi