No abstract

No abstract

The embodiment of consciousness in socio-cognitive agents play a significant role in their acceptance as co-partners. Man-machine social interaction’s success is based on the agent’s generated believable behaviors. In this regard, such an agent needs to generate realistic beliefs, intentions, goals, self-regulation, verbal, and non-verbal communication (including gestures) according to the context of ongoing interaction is very important. This study hypothesizes that the implementation of the Theory of mind (TOM) may allow the agent to change its intentions, beliefs, and desires by predicting the existing perspective and mental states of the other agents involved in the given social interaction. To study the complexity of dynamics in a social context we have taken the case study of the ‘paper-scissor-rock’ game and developed a cognitive agent capable of using gestures for non-verbal communication following the Theory of mind. This work is in progress and is being developed on the iCub robot simulation. We have used tapped delay line neural networks as the basis for reinforcement learning and strategic planning. This paper will report the cognitive model, neural network initial results obtained.

Vehicle and driver license registration is one of the many commodities that contribute significantly to the revenue generation capabilities of Ghana. However according to the investigation carried out for this research, 86.3 percent of respondents attest to the existence of fake vehicle and driver licenses. Thus, the government of Ghana loses a lot when it comes to generating revenue from Driver and Vehicle Licensing Authority. This research found out a yearly revenue generation capacity from the Tamale office of the Driver and Vehicle Licensing Authority of about GHS1, 440,000 from only vehicle registration, amidst this massive evasion by drivers and vehicle owners.This research unearthed the major factors motivating the menace of non-licensing of vehicles and drivers; it as well exposed the methods by which vehicles are being stolen from their owners, pointing out reasons for vehicle owners' reluctance to report for the recovery of these stolen vehicles. The technology employed for license verification by the security services was not left out.

Most message passing neural networks (MPNNs) are widely used for assortative network representation learning under the assumption of homophily between connected nodes. However, this fundamental assumption is inconsistent with the heterophily of disassortative networks (DNs) in many real-world applications. Therefore, we propose a novel MPNN called NEDA based on neighborhood expansion for disassortative network representation learning (DNRL). Specifically, our NEDA first performs neighborhood expansion to seek more informative nodes for aggregation and then performs data augmentation to speed up the optimization process of a set of parameter matrices at the maximum available training data with minimal computational cost. To evaluate the performance of NEDA comprehensively, we perform several experiments on benchmark disassortative network datasets with variable sizes, where the results demonstrate the effectiveness of our NEDA model. The code is publicly available at https://github.com/xueyanfeng/NEDA.