Report available! Telemetering the telltale signs of power issues of wireless internet relays

The TellTale project was conceived with aim of addressing the problem of measurement and projection of the power uptime duration of wireless internet relays. In rural areas and in areas where such projections are not available, operators often fail to address downtimes in a timely manner, thereby increasing the number and duration of downtimes and/or fail to project the power needs of a relay properly. These issues have direct adverse economic consequences for both providers and users

In line with this, the project objectives were to:
1. Identify an affordable and replicable sensor+SBC + internet uplink power charge and discharge module
2. Create a cloud-based, machine-learning supported, data ingestion, storage, data prep, analysis and reporting system.
3. Develop an easy-to0use reporting and alert system with PC and mobile applications (Android)
4. Measure and report on the cost-saving and improved uptime impact of the project
5. Disseminate the project findings and share the systems design
6. Create a paid support system for interested parties.

The project has achieved most of its objectives. An AirJaldi “TellTale” system, capable of measuring battery voltage and generating indicators and alerts based on the its change over time, has been built, demonstrated and is ready for distribution and sharing. At a device cost of around US $20 (hardware components) the system is affordable, as are the software packages and cloud hosting services required.

AirJaldi will offer TellTale using a Freemium model. Interested users can either download the source codes and manuals at no cost from Github (accessed directly or via our website and those of other partners), or choose one of various models of paid support offered by AirJaldi.

TellTale’s User Interface (UI) was designed to be clear and easy to use and update and is available in both computer and mobile version. An Android APK, offering a stripped-down version of the web UI with a focus on alerts, was also created and made available for users.

We plan to continue working on improving and enriching TellTale in the coming months and will share information and resources.

The final report is available here.

Report Available! Experiment and improve reinforcement learning algorithms to enhance anomalous network behaviour detection

Cybersecurity is a significant research area because all of the operations based on government, military, commercial, financial and civilians gather, process, transfer and store tremendous volume of data on computers and others. Cyber-attacks have imposed increasing threats and damages on our modern society at all levels. Network Intrusion Detection System (NIDS) is one of the major techniques in preventing cyber-attacks occurred in network traffic. Over the past decade, a lot of research work has been conducted to explore the capabilities of artificial intelligence (AI) methods in developing NIDS solutions. The previous studies suggested that AI algorithms have promising potentials in developing effective solutions to detect the increasing attacks.

TeleMARS R&D team commits to advance AI-based methods, explore realistic approaches of deploying the research outcomes in real network environment, and support on-going research in wider community to achieve long term sustainable development. The key objectives of this project were to:

  • contribute to the development of NIDS;
  • contribute to research community in the subject of anomaly detection;
  • establish a practical collaboration framework to enable scientists and IT professionals from diverse background to work together to continuously contribute to NIDS research;
  • test and prove TeleMARS operation and technical frameworks, and the team capabilities; and
  • inspire and enable the participation of broader research community in cybersecurity domain supporting gender equality and inclusion

This project started in September 2020 and finalized in June 2021. The main activities included:

  • Literature review and project design.
  • Data analysis and preparation.
  • Anomaly detection model development using Machine Learning methods including Reinforcement Learning method.
  • Model experimentation.
  • Established evaluation pipelines to simulate real application environment.
  • Model capability evaluation applying different datasets.
  • Implementation of a collaboration framework supporting the research activities conducted by researchers and professionals with various backgrounds.

The final technical report is available for review here.