The development of the Internet of Things (IoT) and intelligent vehicles bring a comfortable environment for users. Various emerging vehicular applications using artificial intelligence (AI) technologies are expected to enrich users’ daily life. However, how to execute computation-intensive applications on resource-constrained vehicles based on AI still faces great challenges. In this paper, we consider the vehicular computation offloading problem in mobile edge computing (MEC), in which multiple mobile vehicles select nearby MEC servers to offload their computing tasks. We propose a multi-agent deep reinforcement learning (DRL) based computation offloading scheme, in which the uncertainty of a multi-vehicle environment is considered so that the vehicles can make offloading decisions to achieve an optimal long-term reward. Firstly, we formalize a formula for the computation offloading problem. The goal of this paper is to determine the optimal offloading decision to MEC server under each observed system state, so as to minimize the total task processing delay in a long-term period. Then, we use a multi-agent DRL algorithm to learn an effective solution to the vehicular task offloading problem. To evaluate the performance of the proposed offloading scheme, a large number of simulations are carried out. The simulation results verify the effectiveness and superiority of the proposed scheme.

Mobile crowdsensing is an emerging paradigm that selects users to complete sensing tasks. Recently, mobile vehicles are adopted to perform sensing data collection tasks in the urban city due to their ubiquity and mobility. In this article, we study how mobile vehicles can be optimally selected in order to collect maximum data from the urban environment in a future period of tens of minutes. We formulate the recruitment of vehicles as a maximum data limited budget problem. The application scenario is generalized to a realistic online setting where vehicles are continuously moving in real-time and the data center decides to recruit a set of vehicles immediately. A deep learning-based scheme through mobile vehicles (DLMV) is proposed to collect sensing data in the urban environment. We first propose a deep learning-based offline algorithm to predict vehicle mobility in a future time period. Furthermore, we propose a greedy online algorithm to recruit a subset of vehicles with a limited budget for the NP-Complete problem. Extensive experimental evaluations are conducted on the real mobility dataset in Rome. The results have not only verified the efficiency of our proposed solution but also validated that DLMV can improve the quantity of collected sensing data compared with other algorithms.

Vehicular Edge Computing (VEC) is a promising paradigm that leverages the vehicles to offload computation tasks to the nearby VEC server with the aim of supporting the low latency vehicular application scenarios. Incentivizing VEC servers to participate in computation offloading activities and make full use of computation resources is of great importance to the success of intelligent transportation services. In this paper, we formulate the competitive interactions between the VEC servers and vehicles as a two-stage Stackelberg game with the VEC servers as the leader players and the vehicles as the followers. After obtaining the full information of vehicles, the VEC server calculates the unit price of computation resource. Given the unit prices announced by VEC server, the vehicles determine the amount of computation resource to purchase from VEC server. In the scenario that vehicles do not want to share their computation demands, a deep reinforcement learning based resource management scheme is proposed to maximize the profits of vehicles and VEC server. The extensive experimental results have demonstrated the effectiveness of our proposed resource management scheme based on Stackelberg game and deep reinforcement learning.

With increasing technological facilities, billions of sensor devices are deployed in the smart city, which allows to sense and collect the status and information of all kinds of infrastructures in the city. Those large number of sensing nodes form many self-organized wireless sensor networks (WSNs). Although the single WSN has been widely studied by researchers. However, few studies have focused on how to effectively connect to Internet of Things (IoT) and collect data in many decentralized WSNs of smart city with a low cost. In this paper, a cluster head rotation joint mobile vehicle data collection (CHR) scheme is proposed to effectively collect data from many decentralized WSNs in smart city with a low cost. In CHR scheme, each WSN selects one or multiple nodes which can connect to mobile vehicles as the cluster heads. Then all the in-network sensor nodes send their data to cluster head through multi-hop communication, due to the cluster head can connect to mobile vehicles, so when mobile vehicles pass by cluster head, the data of cluster head can be sent to mobile vehicles and brought to the data center to process. We first propose a single cluster head rotation joint mobile vehicle data collection (SCHR) scheme to collect data by only using a single CH in a WSN in which the CH rotation and clustering algorithms are carefully designed to balance in-network energy consumption. Then multiple cluster head rotation joint mobile vehicle data collection (MCHR) scheme is proposed to further balance the energy consumption and prolong the network lifetime in which multiple cluster heads are selected to be jointly responsible for the data collection task. The extensive experiments show that the CHR scheme has good performance in the network energy, network lifetime and network transmit capacity.

Medical data have unique specificity and professionalism, requiring substantial domain expertise for their annotation. Precise data annotation is essential for anomaly-detection tasks, making the training process complex. Domain generalization (DG) is an important approach to enhancing medical image anomaly detection (AD). This paper introduces a novel multimodal anomaly-detection framework called MedicalCLIP. MedicalCLIP utilizes multimodal data in anomaly-detection tasks and establishes irregular constraints within modalities for images and text. The key to MedicalCLIP lies in learning intramodal detailed representations, which are combined with text semantic-guided cross-modal contrastive learning, allowing the model to focus on semantic information while capturing more detailed information, thus achieving more fine-grained anomaly detection. MedicalCLIP relies on GPT prompts to generate text, reducing the demand for professional descriptions of medical data. Text construction for medical data helps to improve the generalization ability of multimodal models for anomaly-detection tasks. Additionally, during the text–image contrast-enhancement process, the model’s ability to select and extract information from image data is improved. Through hierarchical contrastive loss, fine-grained representations are achieved in the image-representation process. MedicalCLIP has been validated on various medical datasets, showing commendable domain generalization performance in medical-data anomaly detection. Improvements were observed in both anomaly classification and segmentation metrics. In the anomaly classification (AC) task involving brain data, the method demonstrated a 2.81 enhancement in performance over the best existing approach.

Object detection is a fundamental task in computer vision, which is usually based on convolutional neural networks (CNNs). While it is difficult to be deployed in embedded devices due to the huge storage and computing consumptions, binary neural networks (BNNs) can execute object detection with limited resources. However, the extreme quantification in BNN causes diversity of feature representation loss, which eventually influences the object detection performance. In this paper, we propose a method balancing Information Retention and Deviation Control to achieve effective object detection, named IR-DC Net. On the one hand, we introduce the KL-Divergence to compose multiple entropy for maximizing the available information. On the other hand, we design a lightweight convolutional module to generate scale factors dynamically for minimizing the deviation between binary and real convolution. The experiments on PASCAL VOC, COCO2014, KITTI, and VisDrone datasets show that our method improved the accuracy in comparison with previous binary neural networks.