Classification of Data Stream in Sensor Network With Small Samples

Compared with conventional narrowband radar, ultra-wideband (UWB) radar has strong anti-interference performance, low-frequency, and wide-frequency characteristics, a good penetrating ability, a high-resolution range, and a good target-recognition ability. It is effective for the detection of weak signals such as breathing or motion of the human body. Therefore, a UWB radar is widely used in the field of human body target detection for earthquake and snow disasters. At present, through-wall human target detection technology using a UWB radar has two challenging problems. First, UWB radar data has a dynamic acquisition process, whereas existing detection technologies mostly employ static learning models, resulting in an inability to process and learn data features online. There is a need to address target recognition based on sensor-network data stream. Second, UWB radar faces the problem of unbalanced data classification in the identification of through-wall targets, i.e., target recognition under small-sample conditions. To address these issues, this paper proposes an adaptive incremental recursive least-squares regression parameter estimation method based on an adaptive variable sliding window, which performs Gaussian function fitting on the data streams and adapts to the mean square error and self-adaptation variable sliding window threshold comparison to adaptively block dynamic data streams. The tensor space theory is used to extract and fuse the multisensor data, and the tensor depth learning algorithm is used to improve the recognition accuracy of the target detection under small-sample conditions. To evaluate the feasibility of the proposed algorithm, we use three UWB radars to build a multistate recognition system for human targets. The data stream adaptive block effect, single and multisensor classification effects were tested under small-sample conditions. The experimental results indicate that the proposed algorithm not only accurately segmented the dynamic data streams but also effectively realized multisensor information fusion and improved the real-time target monitoring under small-sample conditions.