Recognizing arabic handwritten characters using deep learning and genetic algorithms

Automated techniques for Arabic content recognition are at a beginning period contrasted with their partners for the Latin and Chinese contents recognition. There is a bulk of handwritten Arabic archives available in libraries, data centers, historical centers, and workplaces. Digitization of these documents facilitates (1) to preserve and transfer the country’s history electronically, (2) to save the physical storage space, (3) to proper handling of the documents, and (4) to enhance the retrieval of information through the Internet and other mediums. Arabic handwritten character recognition (AHCR) systems face several challenges including the unlimited variations in human handwriting and the leakage of large and public databases. In the current study, the segmentation and recognition phases are addressed. The text segmentation challenges and a set of solutions for each challenge are presented. The convolutional neural network (CNN), deep learning approach, is used in the recognition phase. The usage of CNN leads to significant improvements across different machine learning classification algorithms. It facilitates the automatic feature extraction of images. 14 different native CNN architectures are proposed after a set of try-and-error trials. They are trained and tested on the HMBD database that contains 54,115 of the handwritten Arabic characters. Experiments are performed on the native CNN architectures and the best-reported testing accuracy is 91.96%. A transfer learning (TF) and genetic algorithm (GA) approach named “HMB-AHCR-DLGA” is suggested to optimize the training parameters and hyperparameters in the recognition phase. The pre-trained CNN models (VGG16, VGG19, and MobileNetV2) are used in the later approach. Five optimization experiments are performed and the best combinations are reported. The highest reported testing accuracy is 92.88%.

     

Intelligent Machine Learning with Metaheuristics Based Sentiment Analysis and Classification

Sentiment Analysis (SA) is one of the subfields in Natural Language Processing (NLP) which focuses on identification and extraction of opinions that exist in the text provided across reviews, social media, blogs, news, and so on. SA has the ability to handle the drastically-increasing unstructured text by transforming them into structured data with the help of NLP and open source tools. The current research work designs a novel Modified Red Deer Algorithm (MRDA) Extreme Learning Machine Sparse Autoencoder (ELMSAE) model for SA and classification. The proposed MRDA-ELMSAE technique initially performs preprocessing to transform the data into a compatible format. Moreover, TF-IDF vectorizer is employed in the extraction of features while ELMSAE model is applied in the classification of sentiments. Furthermore, optimal parameter tuning is done for ELMSAE model using MRDA technique. A wide range of simulation analyses was carried out and results from comparative analysis establish the enhanced efficiency of MRDA-ELMSAE technique against other recent techniques.     

Modeling and Analysis of UAV-Assisted Mobile Network with Imperfect Beam Alignment

With the rapid development of emerging 5G and beyond (B5G), Unmanned Aerial Vehicles (UAVs) are increasingly important to improve the performance of dense cellular networks. As a conventional metric, coverage probability has been widely studied in communication systems due to the increasing density of users and complexity of the heterogeneous environment. In recent years, stochastic geometry has attracted more attention as a mathematical tool for modeling mobile network systems. In this paper, an analytical approach to the coverage probability analysis of UAV-assisted cellular networks with imperfect beam alignment has been proposed. An assumption was considered that all users are distributed according to Poisson Cluster Process (PCP) around base stations, in particular, Thomas Cluster Process (TCP). Using this model, the impact of beam alignment errors on the coverage probability was investigated. Initially, the Probability Density Function (PDF) of directional antenna gain between the user and its serving base station was obtained. Then, association probability with each tier was achieved. A tractable expression was derived for coverage probability in both Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) condition links. Numerical results demonstrated that at low UAVs altitude, beam alignment errors significantly degrade coverage performance. Moreover, for a small cluster size, alignment errors do not necessarily affect the coverage performance.     

Preparation of Plate‐Like Sodium Niobate Particles by Hydrothermal Method

Sodium niobate NaNbO₃ hydrate (NN‐hydrate) particles with a plate‐like morphology were prepared at 140°C for 2 h in 12 mol/L of NaOH by the hydrothermal method. Bar‐like Na₈Nb₆O₁₉·13H₂O particles were synthesized at as low as 100°C for 2 h. This work demonstrates that by carefully optimizing the reaction condition, we can selectively fabricate niobate structures, including the bar‐like, plate‐like, fibers and cube particles through a direct reaction between NaOH solution and Nb₂O₅. It was found that Nb₆O₁₉^8? formed was an important premise for formation of the NN‐hydrate, and lower [OH^–] was not favorable in preparing the NN‐hydrate as there was an optimum [OH^?]. Through researching effects of the reaction temperature, time, concentration of NaOH, and content of Nb₂O₅ on the NN‐hydrate structure and evolution, the formation mechanism from solid reactants to the intermediate were investigated. After calcining at 800°C, the synthesized NN‐hydrate particles made a phase almost transform to the perovskite NaNbO₃, and the morphology of these calcined particles was still plate‐like.     

Preparation of Morphology‐Controlled Plate‐Like Sodium Niobate Particles by Hydrothermal Synthesis

Sodium niobate (NaNbO₃) particles with plate‐like morphology and hexagonal unit cells were prepared by the hydrothermal method. The result of SEM showed that the hexagonal NaNbO₃ were characterized by plate‐like morphology with a diameter of 5–15 μm and a thickness of 1–2 μm. The crucial influences on the morphology and crystal phase of the NaNbO₃, such as concentration of [OH^?], surfactant, and K⁺:Na⁺ ratio, were established. By further calcination treatment, the plate‐like hexagonal NaNbO₃ particles could be completely transformed into perovskite structure without morphology change. The XRD and EBSD results indicate that the major face of the calcined particles is parallel to the crystallographic (001)_pc (pseudo cubic index) plane. Compared with the traditional high‐temperature molten salt method, this work provides a simpler way to prepare the template for fabricating textured ceramics.     

Probabilistic performance assessment of wind energy conversionsystems

This paper describes the development of a general probabilistic model of an autonomous wind energy conversion system (WECS) composed of several wind turbines (wind farm) connected to a load and a battery storage. The proposed technique allows the simulation of wind farms containing identical or different wind turbines types and considers a bidirectional flow of power in and out of the battery. The model is based upon a simple procedure to estimate the joint probability distribution function of the total available wind power and that of the turbines operating modes due to hardware failure. A methodology is also developed to use the proposed model to determine an upper limit on the size of the battery storage required for a given number of turbines to satisfy the load with a certain expected energy not supplied (EENS). The model can also be used to evaluate the energy purchased from or injected to the grid in the case of grid-connected systems     

Low Temperature Magnetization of Two Dimensional 3He on Three Layers of HD Preplated Graphite

We have measured the low temperature magnetization of submonolayer ³He on three layers of HD preplated graphite. NMR measurement has been performed by progressively adding ⁴He to the system, to prevent ³He atoms from being trapped in substrate heterogeneities and to change the areal density of ³He. The exchange constant (J) is found to have a similar density dependence to that for two layers of HD preplated one. The magnetization in the antiferromagnetic region increases gradually down to 100 K and shows no evidence corresponding to a spin gap.     

Self-care independence in children with neurological disorders: An interactional model of adaptive demands and executive dysfunction.

Objective: To describe a neuropsychological assessment model that proposes executive functioning as a key moderator in the development of self-care independence. Setting: Inpatient and outpatient rehabilitation facilities. Participants: Transition-age youths with congenital and acquired neurological disorders. Intervention: Transition to the adaptive roles and expectations of adulthood can be challenging for adolescents with neurological disorders and other chronic medical conditions. These individuals frequently encounter functional problems related to additional time requirements, new life skill demands, and increased need for organization and planning. In addition, the neuropsychological consequences of these disorders often include deficits in motor speed and coordination as well as executive control (including planning, organization, and working memory). Consideration of the integrity of executive function skills and the presence of atypical adaptive demands is crucial during planning for transition of individuals into self-care independence and development of an approach to assessment and intervention. Conclusions: Rehabilitation psychologists have the potential to improve the quality of life of adolescents with neurological disorders as they transition into adulthood by considering the "executive burden" posed to the individuals by various combinations of executive dysfunction and atypical adaptive demands. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Photocatalytic degradation of diclofenac using hybrid MIL-53(Al)@TiO2 and MIL-53(Al)@ZnO catalysts

In this work, TiO₂ and ZnO were incorporated successfully into a MIL-53(Al) metal–organic framework (MOF) to form nanocomposites via a facile post-modification technique. The hybrid MIL-53(Al)@TiO₂ and MIL-53(Al)@ZnO were characterized by several characterization tests. The X-ray diffraction (XRD), Fourier-transform infrared (FTIR), and field-emission scanning electron microscopy (FE-SEM) analyses showed evidence of the successful incorporation of TiO₂ and ZnO within the MIL-53(Al) framework. The thermal gravimetric analysis (TGA) analysis demonstrated the excellent thermal stability of MIL-53(Al)@TiO₂ and MIL-53(Al)@ZnO, while diffuse reflectance spectroscopy (DRS) determined the direct optical band gaps of MIL-53(Al)@ZnO and MIL-53(Al)@TiO₂ to be 3.24 and 3.34 eV, respectively. The composites were also tested for the photocatalytic degradation of diclofenac (DCF) as a micropollutant. The DCF degradation efficiency of the photocatalysts was ranked in the following order: MIL-53(Al)@TiO₂ > MIL-53(Al) > TiO₂ > ZnO > MIL-53(Al)@ZnO. The incorporation of TiO₂ enhanced the optical properties of MIL-53 (Al), which was confirmed with the superior photodegradation efficiency of MIL-53(Al)@TiO₂ (>85% in 2 h) as compared to the pristine MIL-53(Al) (around 80% in 2 h). The improvement in the photodegradation of the hybrid-MOF is mostly associated with the possible dual function of the adsorption and photodegradation mechanisms. The reusability of MIL-53(Al) and its composites was inspected over 3 cycles of photodegradation experiments with DCF. The photocatalytic activity of MIL-53(Al)@TiO₂ remained unchanged (>90%), while for MIL-53(Al) and MIL-53(Al)@ZnO a slight drop was observed over three cyclic degradation experiments. Fluorescence measurements revealed that the hydroxyl radical is an important reactive oxygen species produced by all the photocatalysts that aid in the photodegradation of DCF. Furthermore, the kinetic modelling of the photoreaction identified a second-order kinetics for all catalysts. Experiments with scavengers showed that hydroxyl radicals played a major role in the photocatalytic process, and it was found that only 2 h of treatment was sufficient to obtain a considerable chemical oxygen demand (COD) reduction of 58%.