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.

Wi-Fi round-trip timing (RTT) was applied to indoor positioning systems based on distance estimation. RTT has a higher reception instability than the received signal strength indicator (RSSI)-based fingerprint in non-line-of-sight (NLOS) environments with many obstacles, resulting in large positioning errors due to multipath fading. To solve these problems, in this paper, we propose high-precision RTT-based indoor positioning system using an RTT compensation distance network (RCDN) and a region proposal network (RPN). The proposed method consists of a CNN-based RCDN for improving the prediction accuracy and learning rate of the received distances and a recurrent neural network-based RPN for real-time positioning, implemented in an end-to-end manner. The proposed RCDN collects and corrects a stable and reliable distance prediction value from each RTT transmitter by applying a scanning step to increase the reception rate of the TOF-based RTT with unstable reception. In addition, the user location is derived using the fingerprint-based location determination method through the RPN in which division processing is applied to the distances of the RTT corrected in the RCDN using the characteristics of the fast-sampling period.

Image captions aim to generate human-like sentences that describe the image’s content. Recent developments in deep learning (DL) have made it possible to caption images for accurate descriptions and detailed expressions. However, since DL learns the relationship between images and captions, it constructs sentences based on commonly frequented words in the dataset. Although these generated sentences are highly accurate, they have low lexical diversity, unlike humans due to limited vocabulary. Therefore, in this paper, we propose a Part-Of-Speech (POS) guidance module and a multimodal-based image captioning model that determines the intensity of images and word sequences and generates sentences through POS to enhance the lexical diversity of DL. The proposed POS guidance module enables rich expression by controlling the information of images and sequences based on the predicted POS guidance to predict words. Then, the POS multimodal layer adds POS and output vector of Bi-LSTM using the multimodal layer to predict the next caption, considering the grammatical structure. We trained and tested the proposed model on the Flicker 30K and MS COCO datasets and compared them with current state-of-the-art studies. Also, we analyzed the lexical diversity of the caption model through the Type-Token Ratio (TTR) and confirmed that the proposed model generates sentences using several words.