In the medical treatment of pneumonia, most patients undergo multiple CT scans at different time points, generating serialised CT data. However, traditional segmentation methods based on convolutional networks are difficult to capture inter-slice dependencies, which can result in missing sequence information. Additionally, Transformer-based segmentation methods tend to overemphasize temporal information, leading to the loss of local features in a single image. To address these issues, we propose a Serialised Pulmonary Lesion Segmentation with Spatiotemporal Transformer (SPLS-STT). Specifically, we firstly capture local features of lesion regions and global features from the serialised lung CT through a self-attention mechanism, which generates a spatial feature maps. Secondly, the obtained spatial feature maps at multiple time points are arranged in chronological order, and the dependencies between the pneumonia lesions at different time points are established by the cross-window temporal attention mechanism. Finally, we combine the features in the temporal and spatial dimensions through the cross-attention mechanism to compensate for the loss of local features during feature extraction in the temporal dimension. Experimental results show that our spatiotemporal Transformer model outperforms the traditional single-dimensional processing methods in terms of accuracy metrics. Furthermore, our model achieves a Dice coefficient of 37.9% on the lung CT sequence dataset, which is an improvement of 9.5% compared to the Vision Transformer.

With a rapid increase in the number of vehicles over recent years, urban parking systems have encountered more and more challenges. In this article, a dual-lens millimeter wave (MMW) radar antenna is designed for a smart parking system in the context of the Internet of Things (IoT). A flat dielectric punch lens is used to increase the gain of the transmitting antenna in order to compensate for the penetration loss in MMW. In addition, a dielectric rod lens is used to correct beam direction and maintain a wide beamwidth in order to overcome received energy loss due to scattering of the car chassis. The combined dual-lens antenna can improve the accuracy and stability of MMW radar operating at 24 GHz. The measured gain is 15.8 dBi for the transmitting antenna and 7.9 dBi for the receiving antenna, and the 3-dB beamwidth is approximately 65°. The system measurement results show that the proposed antenna has stable measurement effect and is suitable for the MMW radar smart parking system.

With the development of the economy, products are significantly enriched, and uncertainty has been their inherent quality. The probabilistic dynamic skyline (PDS) query is a powerful tool for customers to use in selecting products according to their preferences. However, this query suffers several limitations: it requires the specification of a probabilistic threshold, which reports undesirable results and disregards important results; it only focuses on the objects that have large dynamic skyline probabilities; and, additionally, the results are not stable. To address this concern, in this paper, we formulate an uncertain dynamic skyline (UDS) query over a probabilistic product set. Furthermore, we propose effective pruning strategies for the UDS query, and integrate them into effective algorithms. In addition, a novel query type, namely the top$k$favorite probabilistic products (TFPP) query, is presented. The TFPP query is utilized to select$k$products which can meet the needs of a customer set at the maximum level. To tackle the TFPP query, we propose a TFPP algorithm and its efficient parallelization. Extensive experiments with a variety of experimental settings illustrate the efficiency and effectiveness of our proposed algorithms.

Query processing over uncertain data has gained growing attention, because it is necessary to deal with uncertain data in many real-life applications. In this paper, we investigate skyline queries over uncertain data in distributed environments (DSUD query) whose research is only in an early stage. The state-of-the-art algorithm, called e-DSUD algorithm, is designed for processing this query. It has the desirable characteristics of progressiveness and minimum bandwidth consumption. However, it still needs to be perfected in three aspects. (1) Progressiveness. Each time it only returns one query result at most. (2) Efficiency. There are a significant amount of redundant I/O cost and numerous iterations which causes a long total query time. (3) Universality. It is restricted to the case where local skyline tuples are incomparability. To address these concerns, we first present a detailed analysis of the e-DSUD algorithm and then develop an improved framework for the DSUD query, namely IDSUD. Based on the new framework, we propose an adaptive algorithm, called ADSUD, for the DSUD query. In the algorithm, we redefine the approximate global skyline probability and choose local representative tuples due to minimum probabilistic bounding rectangle adaptively. Furthermore, we design a progressive pruning method and apply the reuse mechanism to improve its efficiency. The results of extensive experiments verify the better overall performance of our algorithm than the e-DSUD algorithm.