The development aspects of rich web-based applications have evolved; however, abstract concepts, like styles and patterns, are still lacking. If an abstract style for rich web-based applications is available, it can support the whole engineering process in many ways, like assisting in designing aspects and the system’s evolution. We have produced an abstract architectural style named RiWAArch style for standard rich web-based applications, and we are working on extending the same to realize integrating push-communication. Push-communication has become a contemporary requirement in developing features like real-time notifications in rich web-based applications. However, the features to be expected from a style to realize the integration of the push-communication are not yet recognized. This concept paper proposes a set of features to be expected from a style for push-communication-integrated rich web-based applications. Our ongoing research will later utilize these features to form requirements and design a comprehensive style by extending the RiWAArch style to realize the abstract features of integrating true push-communication into rich web-based applications.

Due to the popularity of the Computer science field many students study programming. With large numbers of student enrollments in undergraduate courses, assessing programming submissions is becoming an increasingly tedious task that requires high cognitive load, and considerable amount of time and effort. Programming assignments usually contain algorithmic implementations written in specific programming languages to assess students' logical thinking and problem-solving skills. Evaluators use either a test case-driven or source code analysis approach when evaluating programming assignments. Given that many marking rubrics and evaluation criteria provide partial marks for programs that are not syntactically correct, evaluators are required to analyze the source code during evaluations. This extra step adds additional burden on evaluators that consumes more time and effort. Hence, this research work attempts to study existing automatic source code analysis mechanisms, specifically, use of deep learning approaches in the domain of automatic assessments. Such knowledge may lead to creating novel automated marking models using past student data and apply deep learning techniques to implement automatic assessments of programming assignments irrespective of the computer language or the algorithm implemented.

Attention is the fundamental element of effective learning, memory, and interaction. Learning however, with the evolvement of technologies in the modern digital age, has surpassed traditional learning systems to more convenient online or e-learning systems. Nevertheless, unlike in the traditional learning systems, attention detection of a student in an e-learning environment remains one of the barely explored areas in Human Computer Interaction. This study proposes a multimodal ensemble solution to detect the level of attentiveness of a student in an e-learning environment, with the use of computer vision, natural language processing, and deep learning to overcome the barriers in identifying user attention in e-learning. The proposed multimodal captures, processes, and predicts user attentiveness levels of individual students, which are subsequently aggregated through an ensemble model to derive an overall outcome of better accuracy than individual model outcomes. The final outcome of the ensemble model produces a range of percentages, within which the attentiveness level of the student lies during a single online lesson. This range is consequently delivered to the users through an Application Programming Interface.

The elderly population constitutes a large percentage of the society hence making elderly care a top priority. Falls have been identified as a leading issue among major problems faced by them. Concerning this, many monitoring devices have been developed, most of them focusing solely on one specific health care aspect or related to fall detection, and are based on sensors and wearable devices which are usually uncomfortable for daily use. Considering these aspects, the solution proposed in this research is a real time computer vision-based system that monitors behavior and detects anomalies through deep learning. The monitoring is mainly focused on detecting unusual behavior including falls, and monitoring routine activities to detect deviations. A device approach is used to deploy the deep learning models and consists of IP camera-based monitoring which uses a special privacy protected procedure that ensures the detection is done based on meta data and therefore no camera image or footage is stored. The research is mainly focused on four major components which are user identification, fall detection, routine variance detection and device configuration.

Genetic Algorithm (GA) is a widely adopted optimization technique under evolutionary optimization. Inspired by the evolutionary operators of selection, crossover and mutation, Genetic Algorithms have been used to successfully solve myriad optimization problems in a wide range of domains, including in optimizing multi-agent systems. On the other hand, Evolutionary Game Theory (EGT) is used to model social-economic systems by mimicking social evolution by adopting neighborhood strategies in a stochastic manner. In this work, an extended GA is proposed for multi-agent systems, which incorporates the strategy adoption in EGT into GA enabled multi-agent systems. The proposed extended GA algorithm is applied to an example multi-robot navigation application. The proposed algorithm gives promising results in terms of the convergence time, compared to the GA based approach. Possible applications of the proposed algorithm are also discussed, while indicating potential future research directions.

Social systems are increasingly being modelled as complex networks, and the interactions and decision making of individuals in such systems can be modelled using game theory. Therefore, networked game theory can be effectively used to model social dynamics. Individuals can use pure or mixed strategies in their decision making, and recent research has shown that there is a connection between the topological placement of an individual within a social network and the best strategy they can choose to maximise their returns. Therefore, if certain individuals have a preference to employ a certain strategy, they can be swapped or moved around within the social network to more desirable topological locations where their chosen strategies will be more effective. To this end, it has been shown that to increase the overall public good, the cooperators should be placed at the hubs, and the defectors should be placed at the peripheral nodes. In this paper, we tackle a related question, which is the time (or number of swaps) it takes for individuals who are randomly placed within the network to move to optimal topological locations which ensure that the public utility satisfies a certain utility threshold. We show that this time depends on the topology of the social network, and we analyse this topological dependence in terms of topological metrics such as scale-free exponent, assortativity, clustering coefficient, and Shannon information content. We show that the higher the scale-free exponent, the quicker the public utility threshold can be reached by swapping individuals from an initial random allocation. On the other hand, we find that assortativity has negative correlation with the time it takes to reach the public utility threshold. We find also that in terms of the correlation between information content and the time it takes to reach a public utility threshold from a random initial assignment, there is a bifurcation: one class of networks show a positive correlation, while another shows a negative correlation. Our results highlight that by designing networks with appropriate topological properties, one can minimise the need for the movement of individuals within a network before a certain public good threshold is achieved. This result has obvious implications for defence strategies in particular.

Influence models enable the modelling of the spread of ideas, opinions and behaviours in social networks. Bounded rationality in social network suggests that players make non optimum decisions due to the limitations of access to information. Based on the premise that adopting a state or an idea can be regarded as being 'rational', we propose an influence model based on the heterogeneous bounded rationality of players in a social network. We employ the quantal response equilibrium model to incorporate the bounded rationality in the context of social influence. The bounded rationality of following a seed or adopting the strategy of a seed would be negatively proportional to the distance from that node. This indicates that the closeness centrality would be the appropriate measure to place influencers in a social network. We argue that this model can be used in scenarios where there are multiple types of influencers and varying payoffs of adopting a state. We compare different seed placement mechanisms to compare and contrast the optimum method to minimise the existing social influence in a network when there are multiple and conflicting seeds. We ascertain that placing of opposing seeds according to a measure derived from a combination of the betweenness centrality values from the seeds and the closeness centrality of the network would provide the maximum negative influence.

We study evolution of coordination in social systems by simulating a coordination game in an ensemble of scale-free and small-world networks and comparing the results. We give particular emphasis to the role information about the pay-offs of neighbours plays in nodes adapting strategies, by limiting this information up to various levels. We find that if nodes have no chance to evolutionarily adapt, then non-coordination is a better strategy, however when nodes adapt based on information of the neighbour payoffs, coordination quickly emerges as the better strategy. We find phase transitions in number of coordinators with respect to the relative pay-off of coordination, and these phase transitions are sharper in small-world networks. We also find that when pay-off information of neighbours is limited, small-world networks are able to better cope with this limitation than scale-free networks. We observe that provincial hubs are the quickest to evolutionarily adapt strategies, in both scale-free and small world networks. Our findings confirm that evolutionary tendencies of coordination heavily depend on network topology.

Mixing patterns in social networks can give us important clues about the structure and functionality of these networks. In the past, a number of measures including variants of assortativity have been used to quantify degree mixing patterns of networks. In this paper, we are interested in observing the heterogeneity of the neighbourhood of nodes in networks. For this purpose, we use the standard deviation of degree differences between a node and its neighbours. We call this measure the 'versatility' of a node. We apply this measure on synthetic and real world networks. We find that among real world networks three classes emerge -(i) Networks where the versatility converges to non-zero values with node degree (ii) Networks where the versatility converges to zero with node degree (iii) Networks where versatility does not converge with node degree. We find that there may be some correlation between this and network density, and the geographical / anatomical nature of networks may also be a factor. We also note that versatility could be applicable to any quantifiable network property, and not just node degree.

In this paper, we explore the effect of encircling behaviour on the topology of complex networks. We introduce the concept of topological encircling, which we define as an attacker making links to neighbours of a victim with the ultimate aim of undermining that victim. We introduce metrics to quantify topological encircling in complex networks, both at the network level and node pair (link) level. Using synthesized networks, we demonstrate that our measures are able to distinguish intentional topological encircling from preferential mixing. We discuss the potential utility of our measures and future research directions.