We show that standard machine learning algorithms may be trained to predict certain invariants of low genus arithmetic curves. Using datasets of size around 105, we demonstrate the utility of machine learning in classification problems pertaining to the BSD invariants of an elliptic curve (including its rank and torsion subgroup), and the analogous invariants of a genus 2 curve. Our results show that a trained machine can efficiently classify curves according to these invariants with high accuracies (>0.97). For problems such as distinguishing between torsion orders, and the recognition of integral points, the accuracies can reach 0.998.

In the disaster recovery process, sufficient data rate and connectivity should be needed. Thus, in this paper, we propose a file transfer framework with multipath transfer in heterogeneous networks for disaster recovery. We first address design considerations for multipath transfer in disaster recovery. In the proposed framework, we consider the primary link (the satellite link) and the auxiliary link (the unmanned aerial vehicle link). Information on links used to multipath transfer is managed in the proposed framework. The performance results indicate that the proposed framework can provide the enhanced goodput by the multipath transfer. Furthermore, the bandwidth by the primary link can be steadily provided in the lossy environment.

Satellite communications on the move (SOTM) systems are useful for many commercial and military applications, because they support network connectivity and mobility in very large geographical areas. However, SOTM systems suffer from channel blockage because of pointing errors of the antenna and shadowing by obstructions. This channel blockage reduces the network throughput. In this paper, we address a fully reliable application layer forward error correction (AL-FEC) mechanism for SOTM systems to enhance the network throughput. In particular, we propose an acknowledgement exchange protocol to ensure the reliability of the end-to-end data transfer as well as a transmission control scheme aided by navigation systems to enhance the resource efficiency in the AL-FEC mechanism. The proposed AL-FEC mechanism can predict channel blockage by utilizing navigation systems. The proposed mechanism then makes it possible to suspend the data transmission for the duration of the channel blockage. We also theoretically derive the file transfer time, the goodput, and the resource efficiency to justify the effectiveness of the proposed AL-FEC mechanism. The performance results show that the proposed AL-FEC mechanism can significantly enhance the goodput as compared with that of transmission control protocol. Furthermore, the resource efficiency is improved with the aid of the navigation systems.

Due to the advance of WLAN technology, the use of the multimedia service such as the video streaming service has been increased in the home network or CCTV monitoring for cars or construction materials. However, we need to study the method which decreases the transmission delay and the frame loss rate to provide QoS of the video streaming service. Therefore, this paper proposes an active buffer management scheme to guarantee QoS of the video streaming service in the IEEE 802.11e EDCA. The proposed scheme discards the frame in the HoL(Head of Line) of the buffer based on the priority of each frame and the virtual transmission delay of frame newly arriving at the buffer. In the simulation results, the proposed scheme not only decreases the frame loss probability of important I and P frames but also stabilizes the transmission delay. It may increase the QoS of video streaming services.