No abstract

No abstract

Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes. In this paper, the problem of training a two-layer SNN is studied for the purpose of classification, under a Generalized Linear Model (GLM) probabilistic neural model that was previously considered within the computational neuroscience literature. Conventional classification rules for SNNs operate offline based on the number of output spikes at each output neuron. In contrast, a novel training method is proposed here for a first-to-spike decoding rule, whereby the SNN can perform an early classification decision once spike firing is detected at an output neuron. Numerical results bring insights into the optimal parameter selection for the GLM neuron and on the accuracy-complexity trade-off performance of conventional and first-to-spike decoding.

No abstract

Internet of Things (IoT) is turning into an essential part of daily life, and numerous IoT-based scenarios will be seen in future of modern cities ranging from small indoor situations to huge outdoor environments. In this era, navigation continues to be a crucial element in both outdoor and indoor environments, and many solutions have been provided in both cases. On the other side, recent smart objects have produced a substantial amount of various data which demands sophisticated data mining solutions to cope with them. This paper presents a detailed review of previous studies on using data mining techniques in indoor navigation systems for the loT scenarios. We aim to understand what type of navigation problems exist in different IoT scenarios with a focus on indoor environments and later on we investigate how data mining solutions can provide solutions on those challenges.