In distributed manufacturing environments, Auto-mated Guided Vehicles (AGVs) equied with visual camera play a crucial role in automating material handling and optimizing production efficiency. Detecting anomalies during AGV operation is crucial to prevent potential malfunctions that could disrupt industrial processes. However, anomaly detection is challenging due to privacy concerns and the heterogeneity of data collected by AGVs across different factories. While sharing data across factories can improve the generalization capabilities of models, this can lead to overgeneralization in reconstruction-based anomaly detection, where the model reconstructs both normal and anomalous data too well, reducing its ability to detect anomalies. To address this problem, we propose FedCali, a federated learning framework that balances generalization and specialization across AGVs monitoring different manufacturing processes. Our proposed Gradient Guiding Mechanism (GGM) selectively aligns local model gradients with global knowledge only when necessary. This allows local models to retain their unique characteristics while benefiting from shared insights. Experiments with the MVTec dataset show that FedCali improves both reconstruction quality and anomaly detection accuracy, achieving higher AUROC scores and lower losses compared to baseline methods. This shows that FedCali is able to effectively process various manufacturing data collected by AGVs while maintaining data privacy.

We in this paper explore a new data dissemination framework in Mobile P2P networks. Previous works in the literature usually elaborated upon the reduction of dissemination frequency in the network. However, many important and practical issues remain unresolved. First, the success of the system design usually relies on the support of other hardware components such as GPS, causing the extra power consumption. In addition, the property of the physical media used to make the ad-hoc network is not well discussed in the system. The system which assumes all users can access WiFi or 3G everywhere will limit the grow of the system popularity. Most importantly, the user preference is not considered, and each peer will receive and help to broadcast all messages whether the user is interested in. In this paper, we propose the MobiPAD framework, which the current stage concentrates on applications of data dissemination in student communities. The MobiPAD framework is built based on Bluetooth since Bluetooth is low power consumption and high penetration rate, and is suitable for students without the expensive 3G or WiFi accessibility. We also consider preference-aware disseminations to support various user preferences in the Mobile P2P network. The fairness issue is considered in the model, meaning that users who receive more interesting messages should contribute more message retransmission than users who wonder to receive few messages. The basic MobiPAD platform for student communities is also discussed in the paper, to show its possibility for further use.

The mobile social networking application is aimed to build an application that helps users to check-in places and save the check-in data on cloud. Users can then show their trajectory on a web site. This project is ideal for people who spend a great deal of time traveling. The major benefit is the privacy that it offers and the algorithms that help the user to save the battery life. All the data is store in the Google Cloud SQL.

Spatio-temporal databases aim at combining the spatial and temporal characteristics of data. The continuous K-Nearest Neighbor (CKNN) query is an important type of spatio-temporal query that finds the K-Nearest Neighbors (KNNs) of a moving query object at each time instant within a given time interval [ts, te]. In this paper, we investigate how to process a CKNN query efficiently under the situation that each object moves with an uncertain velocity. This uncertainty on the velocity of each object inevitably results in high complexity of the CKNN problem. We propose a cost-effective PKNN algorithm to tackle the complicated problem incurred by this uncertainty.

We refer "time-constrained services” to those requests that have to be replied to within a certain client-expected time duration. If the answer cannot reach the client within this expected time, the value of the information may seriously degrade or even become useless. On-demand channels may not be able to handle all time-constrained services without degrading the performance. How to handle these services in broadcast channels becomes crucial to balance the load of wireless systems. In this paper, we study this problem and find the minimum number of broadcast channels required for such a task. Also, we propose solutions for this problem when the available channels are insufficient. Our performance result reveals that only a moderate number of channels is required to promote these time-constrained services.