Scielo RSS http://www.scielo.org.za/rss.php?pid=1991-169620210002&lang=en vol. 112 num. 2 lang. en http://www.scielo.org.za/img/en/fbpelogp.gif http://www.scielo.org.za http://www.scielo.org.za/scielo.php?script=sci_arttext&pid=S1991-16962021000200001&lng=en&nrm=iso&tlng=en In this paper, a bit-level decoder is presented for soft-input soft-output iterative decoding of Reed-Solomon (RS) codes. The main aim for the development of the proposed algorithm is to reduce the complexity of the decoding process, while yielding a relatively good error correction performance, for the efficient use of RS codes. The decoder utilises information set decoding techniques to reduce the computational complexity cost by lowering the iterative convergence rate during the decoding process. As opposed to most iterative bit-level soft-decision decoders for RS codes, the proposed algorithm is also able to avoid the use of belief propagation in the iterative decoding of the soft bit information, which also contributes to the reduction in the computational complexity cost of the decoding process. The performance of the proposed decoder is investigated when applied to short RS codes. The error correction simulations show the proposed algorithm is able to yield a similar performance to that of the Adaptive Belief Propagation (ABP) algorithm, while being a less complex decoder. http://www.scielo.org.za/scielo.php?script=sci_arttext&pid=S1991-16962021000200002&lng=en&nrm=iso&tlng=en In this paper, a bit-level decoder is presented for soft-input soft-output iterative decoding of Reed-Solomon (RS) codes. The main aim for the development of the proposed algorithm is to reduce the complexity of the decoding process, while yielding a relatively good error correction performance, for the efficient use of RS codes. The decoder utilises information set decoding techniques to reduce the computational complexity cost by lowering the iterative convergence rate during the decoding process. As opposed to most iterative bit-level soft-decision decoders for RS codes, the proposed algorithm is also able to avoid the use of belief propagation in the iterative decoding of the soft bit information, which also contributes to the reduction in the computational complexity cost of the decoding process. The performance of the proposed decoder is investigated when applied to short RS codes. The error correction simulations show the proposed algorithm is able to yield a similar performance to that of the Adaptive Belief Propagation (ABP) algorithm, while being a less complex decoder. http://www.scielo.org.za/scielo.php?script=sci_arttext&pid=S1991-16962021000200003&lng=en&nrm=iso&tlng=en In this research supercapacitors were fabricated using graphene oxide (GO) as the electrode material. GO was synthesized using natural graphite precursor with varying flake sizes. GO was characterized by High-Resolution Transmission Electron Microscopy (HRTEM), Elemental Analysis, Fourier Transform Infrared (FTIR) spectroscopy and Raman spectroscopy. Cyclic voltammetry was carried out at different scan rates to determine the specific capacitance and energy density of the electrode material. An increase in specific capacitance was seen with an increase in graphite precursor flake size. A specific capacitance and energy density of 204.22 F.g-1 and 102.11 kJ.kg-1 respectively at scan rate 10 mV.s-1 was obtained for the GO sample synthesized from graphite precursor with an average particle size of 0.45 mm. This sample also had the highest specific capacitance for all scan rates. http://www.scielo.org.za/scielo.php?script=sci_arttext&pid=S1991-16962021000200004&lng=en&nrm=iso&tlng=en This paper proposes an improved Q-learning method to obtain near-optimal schedules for grid and battery power in a grid-connected electric vehicle charging station for a 24-hour horizon. The charging station is supplied by a solar PV generator with a backup from the utility grid. The grid tariff model is dynamic in line with the smart grid paradigm. First, the mathematical formulation of the problem is developed highlighting each of the cost components considered including battery degradation cost and the real-time tariff for grid power purchase cost. The problem is then formulated as a Markov Decision Process (MDP), i.e., defining each of the parts of a reinforcement learning environment for the charging station's operation. The MDP is solved using the improved Q-learning algorithm proposed in this paper and the results are compared with the conventional Q-learning method. Specifically, the paper proposes to modify the action-space of a Q-learning algorithm so that each state has just the list of actions that meet a power balance constraint. The Q-table updates are done asynchronously, i.e., the agent does not sweep through the entire state-space in each episode. Simulation results show that the improved Q-learning algorithm returns a 14% lower global cost and achieves higher total rewards than the conventional Q-learning method. Furthermore, it is shown that the improved Q-learning method is more stable in terms of the sensitivity to the learning rate than the conventional Q-learning. http://www.scielo.org.za/scielo.php?script=sci_arttext&pid=S1991-16962021000200005&lng=en&nrm=iso&tlng=en In this paper novel semi-automated and fully automated ear-based biometric authentication systems are proposed. The region of interest (ROI) is manually specified and automatically detected within the context of the semi-automated and fully automated systems, respectively. The automatic detection of the ROI is facilitated by a convolutional neural network (CNN) and morphological postprocessing. The CNN classifies sub-images of the ear in question as either foreground (part of the ear shell) or background (homogeneous skin, hair or jewellery). Prominent contours associated with the folds of the ear shell are detected within the ROI. The discrete Radon transform (DRT) is subsequently applied to the resulting binary contour image for the purpose of feature extraction. Feature matching is achieved by implementing an Euclidean distance measure. A ranking verifier is constructed for the purpose of authentication. In this study experiments are conducted on two independent ear databases, that is (1) the Mathematical Analysis of Images (AMI) ear database and (2) the Indian Institute of Technology (IIT) Delhi ear database. The results are encouraging. Within the context of the proposed semi-automated system, accuracies of 99.20% and 96.06% are reported for the AMI and IIT Delhi ear databases respectively. http://www.scielo.org.za/scielo.php?script=sci_arttext&pid=S1991-16962021000200006&lng=en&nrm=iso&tlng=en An image can be described by the objects within it, and interactions between those objects. A pair of object labels together with an interaction label is known as a visual relationship, and is represented as a triplet of the form (subject, predicate, object). Recognising visual relationships in images is a challenging task, owing to the combinatorially large number of possible relationship triplets, which leads to an extreme multi-class classification problem. In addition, the distribution of visual relationships in a dataset tends to be long-tailed, i.e. most triplets occur rarely compared to a small number of dominating triplets. Three strategies to address these issues are investigated. Firstly, instead of predicting the full triplet, models can be trained to predict each of the three elements separately. Secondly a multitask learning strategy is investigated, where shared network parameters are used to perform the three separate predictions. Thirdly, a class-selective mini-batch construction strategy is used to expose the network to more of the rare classes during training. Experiments demonstrate that class-selective mini-batch construction can improve performance on classes in the long tail of the data distribution, possibly at the expense of accuracy on the small number of dominating classes. It is also found that a multitask model neither improves nor impedes performance in any significant way, but that its smaller size may be beneficial. In an effort to better understand the behaviour of the various models, a novel evaluation approach for visual relationship recognition is introduced. We conclude that the use of semantics can be helpful in the modelling and evaluation process. http://www.scielo.org.za/scielo.php?script=sci_arttext&pid=S1991-16962021000200007&lng=en&nrm=iso&tlng=en Despite growing interest in human-machine collaboration for enhanced decision-making, little work has been done on the optimal fusion of human and machine decisions for cost-sensitive biometric authentication. An elegant and robust protocol for achieving this objective is proposed. The merits of the protocol is illustrated by simulating a scenario where a workforce of human experts and a score-generating machine are available for the authentication of handwritten signatures on, for example, bank cheques. The authentication of each transaction is determined by its monetary value and the quality of the claimed author's signature. A database with 765 signatures is considered, and an experiment that involves 24 human volunteers and two different machines is conducted. When a reasonable number of experts are kept in the loop, the average expected cost associated with the workforce-machine hybrid is invariably lower than that of the unaided workforce and that of the unaided machine.