An Automatically Tailored Experience

Digital games need to keep players engaged. Since games are interactive media, achieving this goal means that game designers need to anticipate player actions to create a pre-designed experience. Traditionally, developers have achieved this by restricting player freedom to a strict set of actions thereby curating player experience and ensuring the fun factor. However, games are taking a different route with more users making their own content (User Generated Content, UGC) through extensive creativity tools which make it hard to predict player experience.

Vincent E. Farrugia
Vincent E. Farrugia

To overcome these challenges Vincent E. Farrugia (supervised by Prof. Georgios N. Yannakakis), merged game design and artificial intelligence (AI). He developed a software framework for handling player engagement in environments which feature user generated content and groups. The three pronged solution tackles problems during game production, playing the game itself, and making sure the framework is sustainable. To maintain engagement within groups he analysed data for a particular person within the group but also patterns common across the whole group. Farrugia created software tools, autonomous AI aids, and tools to test and support the framework.

The software framework is made up of inter-operating modules. Firstly, an engagement policy module allows designers to specify theories to express their vision of positive game engagement. Player modelling then shapes this backbone to specific player engagement needs. The module can autonomously learn from player creations as reactions to game stimuli. Individual and group manager modules use this mixture of expert knowledge, AI learnt data, and player game-play history to automatically adapt game content to solve player engagement problems. This procedural content generation (PCG) is tailored for a specific player and time.

The framework’s abilities were showcased in a digital game also developed by Farrugia. Various technologies were incorporated to encourage player creativity in group sessions and to enhance networking. The setup also allowed the AI to quickly learn from each player via parallelism. Initial testing used a simulated environment with software agents. Preliminary testing on real players followed. The simulation was through a personality system to validate the underlying algorithms under various conditions. The resulting diverse game-play styles provide suggestions for AI model improvement. Farrugia is enthusiastic about future work for this AI framework and giving developers better tools to allow player creativity to flourish while maintaining positive game-play experiences. 

This research was performed as part of a Master of Science degree at the Institute of Digital Games, University of Malta. It was partly funded by the Strategic Educational Pathways Scholarship (Malta), which is part-financed by the European Union—European Social Fund (ESF) under Operational Programme II—Cohesion Policy 2007—2013, ‘Empowering People for More Jobs and a Better Quality of Life’.

Smaller, Faster, and just as pretty

Video streaming uses a lot of  bandwidth. Internet service providers can either limit bandwidth or provide more. To bypass this problem newer encoders aim to compact video into smaller packages, to keep the same video quality but a smaller size. 

The problem is the variety of video devices available that range from mobiles, tablets, and high definition TVs. This diversity results in various different video transmissions being needed. To avoid encoding the same sequence several times and reduce the traffic over a network, video coding called H.264/Scalable Video Coding (SVC) was introduced. This type of video coding allows a single stream to encode for time, space, and quality. This technology saves bandwidth. SVC is expected to become the standard for Internet streaming. The only thing holding it back is the need for a complex encoder.

Kurt Abela
Kurt Abela

Kurt Abela (supervised by Dr Ing. Reuben Farrugia) proposed the use of a Graphics Processing Unit (GPU) based encoder to speed up the encoder. The Block Motion Estimation (BME) module within SVC takes up the bulk of the total encoding time in standard H.264/AVC. Abela designed certain modules to be optimised for NVIDIA GPUs. Through an asynchronous programming model, the video encoder could be run simultaneously on the CPU (Computer Processing Unit) and GPU. By using this novel encoder, encoding was sped up at most 436x times, when compared to a reference model, with no loss in quality. The encoder was sped up even more with further improvements to allow real-time HD video encoding. 

This system is much cheaper and easier to use than leading alternatives. GPUs are very cheap and already found in most computers. Further developments on GPUs could soon see them replace more expensive encoders in datacentres.

This research was performed as part of a Masters of Science in Information and Communication Technology at the Faculty of Information and Communication Technology, University of Malta. The research is partially funded by the Strategic Educational Pathways Scholarship Scheme (Malta). The scholarship is part-financed by the European Union—European Social Fund, under Operational Programme II—Cohesion Policy 2007–2013, ‘Empowering People for More Jobs and a Better Quality of Life’.

Maltese Olives and their genes

The olive tree (Olea europaea L.) is one of the oldest species of domesticated trees and the second most important oil fruit crop cultivated worldwide. 97% of the global olive cultivation is concentrated in the Mediterranean Basin. The olive thrives in Maltese soils. Economically, olives are not important for local agriculture, but its cultivation is becoming popular since the Maltese agribusiness has a lot of room for growth to make high quality oil and secondary products. 

Bajda-fruit4-RecoveredIn the Mediterranean region there are two subspecies of Olive tree. These are the wild olive (O. europaea L. subsp. Oleaster) and the cultivated olive (O. europaea L. subsp. Sativa). Each subspecies has several cultivars selected for taste, size, disease resistance or other desirable qualities. There are 1,300 cultivars worldwide and Malta is no exception. The Maltija cultivar is probably the most popular Maltese cultivar and can give a high productivity. The Bidnija cultivar, which is believed to be the oldest Maltese olive cultivar (it is thought to date back to Roman times), produces oil of excellent quality rich in polyphenols (these have many health benefits), exhibits high tolerance to environmental stress such as salinity and drought, and demonstrates resistance to pathogens and pests such as the olive fruit fly. The Bajda variety produces a characteristic white drupe. Besides the native cultivars, there are a number of Maltese wild olives. 

Renowned foreign varieties associated with high productivity tend to have a higher productivity than local cultivars. For this reason, local farmers find foreign varieties more convenient, leaving Malta at risk of forever losing its unique olives.

Till now revival efforts focus on artificial propagation and re-plantation. These trees are identified by their appearance. This is an inaccurate method since olive growth is influenced by environmental conditions.Bidni-fruit-+-leaves

To develop a better way to identify local cultivars, Oriana Mazzitelli (supervised by Dr Marion Zammit Mangion) has focused on adopting a genetic approach. She also wanted to examine the genetic diversity of Maltese olive varieties. Mazzitelli compared the genetic patterns of local varieties to those generated by two commercial Italian (Carolea) and Tunisian varieties (Chemlali). The genetic analysis produced unique DNA profiles that can provide a more accurate means of identification than just looking at the plant.

The genetic variability between varieties was high. The Bidnija and Maltija stood out for their genetic uniqueness. The differences between local varieties suggest that, despite being allegedly native, the origins of the two are not directly linked. A number of DNA marker regions detected in the foreign cultivars and in the Maltese wild olive were undetected in the Maltese cultivars, suggesting that not all DNA markers are present and amplifiable in foreign varieties have been conserved in the Maltese cultivars. Mazzitelli’s work is an important first step to show that local varieties can be identified cheaply through DNA analysis. Without genetic identification, maintaining and cultivating local varieties would be near impossible—a case of genes for good olive oil.


This research is part of a Master of Science in Biochemistry at the Faculty of Medicine and Surgery, University of Malta. The research was funded by STEPS (Strategic Educational Pathways) scholarship which is part-financed by the EU’s European Social Fund (ESF) under Operational Programme II—Cohesion Policy 2007-2013, ‘Empowering People for More Jobs and a Better Quality of Life’.