Accurate point tracking in surgical environments remains challenging due to complex visual conditions, including smoke occlusion, specular reflections, and tissue deformation. While existing surgical tracking datasets provide coordinate information, they lack the semantic context necessary to understand tracking failure mechanisms. We introduce VL-SurgPT, the first large-scale multimodal dataset that bridges visual tracking with textual descriptions of point status in surgical scenes. The dataset comprises 908 in vivo video clips, including 754 for tissue tracking (17,171 annotated points across five challenging scenarios) and 154 for instrument tracking (covering seven instrument types with detailed keypoint annotations). We establish comprehensive benchmarks using eight state-of-the-art tracking methods and propose TG-SurgPT, a text-guided tracking approach that leverages semantic descriptions to improve robustness in visually challenging conditions. Experimental results demonstrate that incorporating point status information significantly improves tracking accuracy and reliability, particularly in adverse visual scenarios where conventional vision-only methods struggle. By bridging visual and linguistic modalities, VL-SurgPT enables the development of context-aware tracking systems crucial for advancing computer-assisted surgery applications that can maintain performance even under challenging intraoperative conditions.

Recent developments of Internet technologies have accelerated the growth of Web services (e.g., open APIs). As many services provide similar functionality, service recommendation systems use the Quality of Service (QoS) to help users find optimal services. Space partition attracts significant attention in service recommendation since it improves the diversity of recommendations and accelerates skyline services query. However, existing partition-based service recommendation systems are all implemented on complete QoS. They are not sufficient when some services’ QoS values are missing or invalid. To this end, we develop a new partition-based service recommendation method on incomplete QoS (named IQSrec) that combines probabilistic skyline query and space partition. The probabilistic skyline query measures top-$k$skyline services on incomplete QoS. A dimension-based partition is specially designed for splitting the incomplete QoS service space into$d$-dimensional partitions with the most representative services. The candidate skyline services are chosen from each partition and merged together for probabilistic skyline computation. IQSrec selects the highest skyline probability services in each partition as recommendations. The experiments on the synthetic and real-world datasets show IQSrec can efficiently recommend skyline services on incomplete QoS. IQSrec has higher accuracy and diversity compared to the state-of-the-art service recommendation approaches.

To improve the efficiency of QoS-centric service selection, skyline query is often used to get small candidates from a large number of services. Recently, interval-valued skyline service selection attracts a lot of attention due to the QoS value fluctuation during execution. To simplify skyline computation, existing interval-valued skyline service selection methods assume the probability density function (PDF) of QoS intervals follows general mathematical distribution, such as the Uniform distribution or the Gaussian distribution, which leads to the inaccurate dominant relationship between QoS intervals. In addition to the impractical assumption of intervals, another problem of existing interval-valued skyline service selection methods is that they are all implemented for complete QoS and are not sufficient when some services’ QoS values are missing or invalid. To this end, we develop a new skyline service selection method on incomplete QoS, named ISkySel, which combines probabilistic skyline query and missing QoS prediction. ISkySel uses valid QoS values to build the PDF of QoS intervals and employs the early termination and sorting techniques to accelerate the probabilistic skyline computation. The experiments on the synthetic and real-world datasets show ISkySel has higher accuracy and efficiency compared to the state-of-the-art skyline service selection.

The Unmanned aerial vehicle (UAV) assisted Internet of Things (IoT) has attracted substantial attention as it is capable of collecting scattered data to meet the stringent demands of emerging IoT applications. Dispatching UAV to collect data from IoT devices (IoTDs) can significantly improve data freshness, which can be measured by Age of Information (AoI). On the other hand, the quantity of IoTDs increases and existing UAV navigation algorithms for dozens of IoTDs can not be applied to massive IoTDs scenarios directly. In this paper, we investigate the AoI minimization problem in massive IoTDs scenarios. Considering unknown traffic patterns of IoTDs, we reformulate the AoI minimization problem as a Markov decision process (MDP). Then we propose a twin delayed deep deterministic policy gradient (TD3) based UAV navigation algorithm to minimize the average AoI of data collected from IoTDs. Simulation results demonstrate that the proposed algorithm can significantly reduce the average AoI in massive IoTDs scenarios when compared with baseline algorithms.