A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN.

Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.

Hyper-Angle Exploitative Searching for Enabling Multi-Objective Optimization of Fog Computing.

Fog computing is an emerging technology. It has the potential of enabling various wireless networks to offer computational services based on certain requirements given by the user. Typically, the users give their computing tasks to the network manager that has the responsibility of allocating needed fog nodes optimally for conducting the computation effectively. The optimal allocation of nodes with respect to various metrics is essential for fast execution and stable, energy-efficient, balanced, and cost-effective allocation. This article aims to optimize multiple objectives using fog computing by developing multi-objective optimization with high exploitive searching. The developed algorithm is an evolutionary genetic type designated as Hyper Angle Exploitative Searching (HAES). It uses hyper angle along with crowding distance for prioritizing solutions within the same rank and selecting the highest priority solutions. The approach was evaluated on multi-objective mathematical problems and its superiority was revealed by comparing its performance with benchmark approaches. A framework of multi-criteria optimization for fog computing was proposed, the Fog Computing Closed Loop Model (FCCL). Results have shown that HAES outperforms other relevant benchmarks in terms of non-domination and optimality metrics with over 70% confidence of the t-test for rejecting the null-hypothesis of non-superiority in terms of the domination metric set coverage.

Knowledge Preserving OSELM Model for Wi-Fi-Based Indoor Localization.

Wi-Fi has shown enormous potential for indoor localization because of its wide utilization and availability. Enabling the use of Wi-Fi for indoor localization necessitates the construction of a fingerprint and the adoption of a learning algorithm. The goal is to enable the use of the fingerprint in training the classifiers for predicting locations. Existing models of machine learning Wi-Fi-based localization are brought from machine learning and modified to accommodate for practical aspects that occur in indoor localization. The performance of these models varies depending on their effectiveness in handling and/or considering specific characteristics and the nature of indoor localization behavior. One common behavior in the indoor navigation of people is its cyclic dynamic nature. To the best of our knowledge, no existing machine learning model for Wi-Fi indoor localization exploits cyclic dynamic behavior for improving localization prediction. This study modifies the widely popular online sequential extreme learning machine (OSELM) to exploit cyclic dynamic behavior for achieving improved localization results. Our new model is called knowledge preserving OSELM (KP-OSELM). Experimental results conducted on the two popular datasets TampereU and UJIndoorLoc conclude that KP-OSELM outperforms benchmark models in terms of accuracy and stability. The last achieved accuracy was 92.74% for TampereU and 72.99% for UJIndoorLoc.