Search

In this paper, we describe our preliminary study for efficient recognition and extraction of named entities on mobile phones. The methodology investigation and experiment verification are focusing on two parts. The first part is a compressed named entities recognition (NER)-model-based named entity recognizer to reduce the memory usage. The second part is an NER classifier. When the result from compressed named entity recognizer is blank, the NER classifier will help to further check if the result is correct to increase the final accuracy. In addition, the framework is described. The study shows that the proposed named entity recognizer remains almost the same recognition performance but reduce the storage cost evidently. Therefore, latter research can dig further in terms of memory usage reduction and performance optimization.

In this paper, we propose a smart water Long Range (Lora) Internet of Things (IoT) System allows operators to monitor water systems in real-time. Applied through both wired and wireless detectors across the systems, it facilitates data analysis, supports user enquiry, and allows timely access to water quality information. In addition, the ultrasound water meter detects water leakage and improves the efficiency of water usage. The water leakage alert system, along with the leakage detection hardware, uses machine learning to solve water leakage problem and improves the service providers' operational efficiency. Currently, ASTRI Smart Water IoT System is successfully deployed in several China Provinces. In 2017, our work received two awards: Asia Pacific ICT Alliance Merit Award and Hong Kong ICT Bronze Award.

Increasingly, Internet services are supported by a large-scale and distributed infrastructure on top of the Internet. This includes Content Delivery Networks (CDNs), Peer-to-peer (P2P) networks for content distribution, and more recently Cloud Computing built out of distributed data centers. Applications include Social networks (e.g. Facebook), content distribution and sharing (e.g. YouTube) and various location-based services and applications (e.g. Google Maps). To ensure proper operation and good QoE, these services need centralized monitoring and control of its operation. In this paper, we report our experience in building such a monitoring system. The key components include a reporting mechanism for capturing the system's state, and a visualization library to help administrator to keep track of how well the system is operating. We applied our monitoring system to support a P2P-assisted video streaming network for broadcasting the 2012 London Olympic Games in Hong Kong. We explain how our system keep track (in real time) of key performance numbers interested by the administrators, such as number of concurrent users, the average rate of contribution from different peers, and the QoE observed at different peer nodes, and illustrate various ways such information is visualized.