Recently, radar-based human activity recognition (HAR) has attracted the attention of researchers as it has been proven that a deep learning (DL) model can be automatically determined by learning a radar dataset. However, unlike general optical image data, the process of collecting and labeling radar data for training the DL model requires considerable manpower and costs. Therefore, an approach that can learn the maximum number of features from a limited radar dataset is essential. Moreover, even if the DL models are trained using a dataset obtained from multiple geometries, performance can be degraded for geometries that are unknown to the trained model. Therefore, we propose a novel radar-based HAR combining a range–time–Doppler (RTD) map and a range-distributed-convolutional neural network (RD-CNN). Unlike the time–Doppler (TD) map, which is mainly used for radar-based HAR, the proposed RTD map provides several human activity-related features by extending the TD map to three dimensions according to the range. The proposed RD-CNN is a new DL model that performs HAR by using the RD layer to extract Doppler features, excluding the range information of RTD map. To verify the performance of the proposed model, experiments were conducted by using the University of Glasgow “radar signatures of human activities,” which is an open dataset for radar-based HAR research. The comparison results of the proposed model and CNNs with the same number of parameters demonstrated a higher recognition accuracy and a lower recognition error even for unknown geometries in the training dataset.

Cracks are common defects that occur on the surfaces of objects and structures. Crack detection is a critical maintenance task that traditionally requires manual labor. Large-scale manual inspections are expensive. Research has been conducted to replace expensive human labor with cheaper computing resources. Recently, crack segmentation based on convolutional neural networks (CNNs) and transformers has been actively investigated for local and global information. However, the transformer is data-intensive owing to its weak inductive bias. Existing labeled datasets for crack segmentation are relatively small. Additionally, a limited amount of fine-grained crack data is available. To address this data-intensive problem, we propose a parallel dual encoder network fusing Pre-Conv-based Transformers and convolutional neural networks (PCTC-Net). The Pre-Conv module automatically optimizes each color channel with a small spatial kernel before the input of the transformer. The proposed model, PCTC-Net, was tested with the DeepCrack, Crack500, and Crackseg9k datasets. The experimental results showed that our model achieved higher generalization performance, stability, and F1 scores than the SOTA model DTrC-Net.

Fingerprinting is the term used to describe a common indoor radio-mapping positioning technology that tracks moving objects in real time. To use this, a substantial number of measurement processes and workflows are needed to generate a radio-map. Accordingly, to minimize costs and increase the usability of such radio-maps, this study proposes an access-point (AP)-centered window (APCW) radio-map generation network (RGN). The proposed technique extracts parts of a radio-map in the form of a window based on AP floor plan coordinates to shorten the training time while enhancing radio-map prediction accuracy. To provide robustness against changes in the location of the APs and to enhance the utilization of similar structures, the proposed RGN, which employs an adversarial learning method and uses the APCW as input, learns the indoor space in partitions and combines the radio-maps of each AP to generate a complete map. By comparing four learning models that use different data structures as input based on an actual building, the proposed radio-map learning model (i.e., APCW-based RGN) obtains the highest accuracy among all models tested, yielding a root-mean-square error value of 4.01 dBm.