Sequence-based Point-Of-Interest (POI) recommendations are increasingly crucial for location-based services and social platforms, offering nuanced insights into predicting user preferences from historical interaction patterns. However, a significant challenge arises from the non-uniform distribution of user-POI interaction sequences, where user preferences are often obscured by irregular and sporadic activities. This paper proposes an innovative Uniform Sequence Balancing (USB) strategy, addressing the critical issue of non-uniform sequences by utilizing the standard deviation of time intervals to achieve uniformity. Our approach transforms non-uniform sequences into uniform ones, thereby facilitating more accurate preference capture. We leverage the Transformer eXtra Long (Transformer-XL) model, known for its ability to discern long-term dependencies, and integrate it with our USB strategy to propose the Sequential Transformer-XL Recommender (STR). Our comprehensive experiments on two widely used public datasets demonstrate the effectiveness of STR, which significantly outperforms state-of-the-art models. The proposed STR not only optimizes recommendation performance but also paves the way for future research on sequence-based recommendation systems.

Sport plays a crucial role in society, influencing physical health, entertainment, and community engagement. As artificial intelligence advances, the ability to classify sport images accurately becomes increasingly crucial. Effective sport image classification enhances applications, such as performance analysis, athlete tracking, and fan engagement. Despite its significance, current methods face challenges due to limited labeled datasets and issues with feature misalignment. This paper introduces a novel Contrastive Language-Image Pre-training (CLIP) based framework specifically designed for sport image classification. By incorporating data augmentation techniques, the approach addresses data sparsity and enriches the diversity of image-text pairings, reducing the need for extensive manual annotation. Additionally, feature alignment strategies tackle text-image misalignment issues that affect classification accuracy. This approach fills a significant research gap and offers practical solutions to improve classification performance in sport image analysis. The results of extensive experiments validate the effectiveness of the framework, demonstrating its potential to advance sports analytics and contribute to more precise and scalable solutions in sport image classification.

The YOLOv5 algorithm is widely used in edge computing systems for object detection. However, the limited computing resources of embedded devices and the large model size of existing deep learning based methods increase the difficulty of real-time object detection on edge devices. To address this issue, we propose a smaller, less computationally intensive, and more accurate algorithm for object detection. Multi-scale Feature Fusion-YOLO (MFF-YOLO) is built on top of the YOLOv5s framework, but it contains substantial improvements to YOLOv5s. First, we design the MFF module to improve the feature propagation path in the feature pyramid, which further integrates the semantic information from different paths of feature layers. Then, a large convolution-kernel module is used in the bottleneck. The structure enlarges the receptive field and preserves shallow semantic information, which overcomes the performance limitation arising from uneven propagation in Feature Pyramid Networks (FPN). In addition, a multi-branch downsampling method based on depthwise separable convolutions and a bottleneck structure with deformable convolutions are designed to reduce the complexity of the backbone network and minimize the real-time performance loss caused by the increased model complexity. The experimental results on PASCAL VOC and MS COCO datasets show that, compared with YOLOv5s, MFF-YOLO reduces the number of parameters by 7% and the number of FLoating point Operations Per second (FLOPs) by 11.8%. The mAP@0.5 has improved by 3.7% and 5.5%, and the mAP@0.5:0.95 has improved by 6.5% and 6.2%, respetively. Furthermore, compared with YOLOv7-tiny, PP-YOLO-tiny, and other mainstream methods, MFF-YOLO has achieved better results on multiple indicators.

In the Internet of Things (IoT) environment, user-service interaction data are often stored in multiple distributed platforms. In this situation, recommender systems need to integrate the distributed user-service interaction data across different platforms for making a comprehensive recommendation decision, during which user privacy is probably disclosed. Moreover, as user-service interaction records accumulate over time, they significantly reduce the efficiency of recommendations. To tackle these issues, we propose a lightweight and privacy-preserving service recommendation approach named SerRec_L2H. In SerRec_L2H, we employ Learning to Hash (L2H) to encapsulate sensitive user-service interaction data into less-sensitive user indices, which facilitates identifying users with similar preferences efficiently for accurate recommendations. We then validate the feasibility of our proposed SerRec_L2H approach through massive experiments conducted on the popular WS-DREAM dataset. The comparative analysis with other competitive approaches demonstrates that our proposal surpasses other approaches in terms ofrecommendation accuracy and efficiency while protecting user privacy.

Edge computing nodes undertake an increasing number of tasks with the rise of business density. Therefore, how to efficiently allocate large-scale and dynamic workloads to edge computing resources has become a critical challenge. This study proposes an edge task scheduling approach based on an improved Double Deep Q Network (DQN), which is adopted to separate the calculations of target Q values and the selection of the action in two networks. A new reward function is designed, and a control unit is added to the experience replay unit of the agent. The management of experience data are also modified to fully utilize its value and improve learning efficiency. Reinforcement learning agents usually learn from an ignorant state, which is inefficient. As such, this study proposes a novel particle swarm optimization algorithm with an improved fitness function, which can generate optimal solutions for task scheduling. These optimized solutions are provided for the agent to pre-train network parameters to obtain a better cognition level. The proposed algorithm is compared with six other methods in simulation experiments. Results show that the proposed algorithm outperforms other benchmark methods regarding makespan.

Service recommendation provides an effective solution to extract valuable information from the huge and ever-increasing volume of big data generated by the large cardinality of user devices. However, the distributed and rich multi-source big data resources raise challenges to the centralized cloud-based data storage and value mining approaches in terms of economic cost and effective service recommendation methods. In view of these challenges, we propose a deep neural collaborative filtering based service recommendation method with multi-source data (i.e., NCF-MS) in this paper, which adopts the cloud-edge collaboration computing paradigm to build recommendation model. More specifically, the Stacked Denoising Auto Encoder (SDAE) module is adopted to extract user/service features from auxiliary user profiles and service attributes. The Multiple Layer Perceptron (MLP) module is adopted to integrate the auxiliary user/service features to train the recommendation model. Finally, we evaluate the effectiveness of the NCF-MS method on three public datasets. The experimental results show that our proposed method achieves better performance than existing methods.