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%.

     

Speech emotion recognition using optimized genetic algorithm-extreme learning machine

Multimedia Tools and Applications - Automatic Emotion Speech Recognition (ESR) is considered as an active research field in the Human-Computer Interface (HCI). Typically, the ESR system is...     

Subcarrier grouping with environmental sensing for MIMO‐OFDM systems over correlated double‐selective fading channels

Multiple‐Input, Multiple‐Output (MIMO)‐orthogonal frequency division multiplexing (OFDM) is a promising technique in 5G wireless communications. In high‐mobility scenarios, the transmission environments are time‐varying and/or the relative moving velocity between the transmitter and receiver is also time‐varying. In the literature, most of previous works mainly focused on fixed subcarrier group size and precoded the MIMO signals with unitary channel state information. In this way, the subcarrier grouping may naturally lead to big loss of channel capacity in high‐mobility scenarios because of the channel state information difference on the subcarriers in each group. To employ the MIMO‐OFDM technique, adaptive subcarrier grouping scheme may be an efficient way. In this paper, we first consider MIMO‐OFDM systems over double‐selective i.i.d. Rayleigh channels and investigate the quantitative relation between subcarrier group size and capacity loss theoretically. With developed theoretical results, we also propose an adaptive subcarrier grouping scheme to satisfy the preset capacity loss threshold by adjusting grouping size with the sensed environmental information and mobile velocity. Theoretical analysis and simulation results show that to achieve a better system capacity, a sparse scattering, lower signal‐to‐noise ratio, and lower velocity as well as properly large antenna number are matched with larger subcarrier group size. One important observation is that if the antenna number is too large and higher than a threshold, which will not bring any additional gain to the subcarrier grouping. That is, the system capacity loss will converge to a lower bound expeditiously with respect to antenna number, which is given in theory also. Copyright © 2016 John Wiley & Sons, Ltd.     

Formal analysis of seamless application execution in mobile cloud computing

Mobile cloud computing augments the resource-constrained mobile devices to run rich mobile applications by leveraging the cloud resources and services. Compute-intensive mobile apps require significant communication resources for migrating the code from mobile devices to the cloud. For such apps, distributed application execution frameworks (DAEF) have been proposed in the literature. These frameworks either migrate the mobile app code during runtime or keep the app synchronized with another remotely executed app on the cloud. Frameworks also support mobile app live migration to cater for compute node mobility. One key research question arises is how successful are these DAEFs in achieving the seamless application execution under various network conditions? The answer to this question entails formal analysis of the DAEFs to determine the realistic bounds on propagation delay, bandwidth and application interaction with mobile device for various types and sizes of apps. In this research, we apply formal analysis techniques to define the execution time of the app and the time required for code migration. We also define three conditions for seamless application execution. Given realistic values for processor speed, application executable size, possible number of executed instructions, network propagation delay and transmission delay, we show what components of the mobile app need to be migrated during execution to the cloud. Finally, we compute realistic bounds for the app size (that can be executed seamlessly) based on important features which include cloud and device resources, bandwidth and latency profile.     

A Bi-population Cooperative Optimization Algorithm Assisted by an Autoencoder for Medium-scale Expensive Problems

This study presents an autoencoder-embedded optimization (AEO) algorithm which involves a bi-population cooperative strategy for medium-scale expensive problems (MEPs). A huge search space can be compressed to an informative low-dimensional space by using an autoencoder as a dimension reduction tool. The search operation conducted in this low space facilitates the population with fast convergence towards the optima. To strike the balance between exploration and exploitation during optimization, two phases of a tailored teaching-learning-based optimization (TTLBO) are adopted to coevolve solutions in a distributed fashion, wherein one is assisted by an autoencoder and the other undergoes a regular evolutionary process. Also, a dynamic size adjustment scheme according to problem dimension and evolutionary progress is proposed to promote information exchange between these two phases and accelerate evolutionary convergence speed. The proposed algorithm is validated by testing benchmark functions with dimensions varying from 50 to 200. As indicated in our experiments, TTLBO is suitable for dealing with medium-scale problems and thus incorporated into the AEO framework as a base optimizer. Compared with the state-of-the-art algorithms for MEPs, AEO shows extraordinarily high efficiency for these challenging problems, thus opening new directions for various evolutionary algorithms under AEO to tackle MEPs and greatly advancing the field of medium-scale computationally expensive optimization.      

Efficient and High-quality Recommendations via Momentum-incorporated Parallel Stochastic Gradient Descent-Based Learning

A recommender system(RS)relying on latent factor analysis usually adopts stochastic gradient descent(SGD)as its learning algorithm.However,owing to its serial mechanism,an SGD algorithm suffers from low efficiency and scalability when handling large-scale industrial problems.Aiming at addressing this issue,this study proposes a momentum-incorporated parallel stochastic gradient descent(MPSGD)algorithm,whose main idea is two-fold:a)implementing parallelization via a novel datasplitting strategy,and b)accelerating convergence rate by integrating momentum effects into its training process.With it,an MPSGD-based latent factor(MLF)model is achieved,which is capable of performing efficient and high-quality recommendations.Experimental results on four high-dimensional and sparse matrices generated by industrial RS indicate that owing to an MPSGD algorithm,an MLF model outperforms the existing state-of-the-art ones in both computational efficiency and scalability.     

Multiconsistency and Robustness with Global Constraints

We propose a natural generalization of arc-consistency, which we call multiconsistency: a value v in the domain of a variable x is k-multiconsistent with respect to a constraint C if there are at least k solutions to C in which x is assigned the value v. We present algorithms that determine which variable-value pairs are k-multiconsistent with respect to several well known global constraints. In addition, we show that finding super solutions is sometimes strictly harder than finding arbitrary solutions for these constraints and suggest multiconsistency as an alternative way to search for robust solutions.Supported by the Danish Research Agency (grant # 272-05-0081).Basic Research in Computer Science, funded by the Danish National Research Foundation.     

Extraction of fetal electrocardiogram using adaptive neuro-fuzzy inference systems

In this paper, we investigate the use of adaptive neuro-fuzzy inference systems (ANFIS) for fetal electrocardiogram (FECG) extraction from two ECG signals recorded at the thoracic and abdominal areas of the mother's skin. The thoracic ECG is assumed to be almost completely maternal (MECG) while the abdominal ECG is considered to be composite as it contains both the mother's and the fetus' ECG signals. The maternal component in the abdominal ECG signal is a nonlinearly transformed version of the MECG. We use an ANFIS network to identify this nonlinear relationship, and to align the MECG signal with the maternal component in the abdominal ECG signal. Thus, we extract the FECG component by subtracting the aligned version of the MECG signal from the abdominal ECG signal. We validate our technique on both real and synthetic ECG signals. Our results demonstrate the effectiveness of the proposed technique in extracting the FECG component from abdominal signals of very low maternal to fetal signal-to-noise ratios. The results also show that the technique is capable of extracting the FECG even when it is totally embedded within the maternal QRS complex.     

Partially bonded near-surface-mounted CFRP bars for strengthened concrete T-beams

A partially bonded strengthening approach for reinforced concrete (RC) beams utilizing near-surface-mounted (NSM) carbon fiber reinforced polymer (CFRP) bars was investigated with the specific objective of improving deformability. A total of six RC T-beams strengthened with NSM CFRP bars of various unbonded lengths were tested. Test results showed a decrease of the stiffness at the post-yield stage of the load–deflection response in the partially bonded beams. This is caused by the delayed increase of the FRP strain within the unbonded length. As a result the beam deformability was increased as the unbonded length increased at the same applied load. Internal slip of the FRP bar and gradual concrete failure were observed near the ultimate state, which caused a complicate nonlinear behavior of the beams. An analytical model is proposed to address the complete beam behavior including the effect of slip of FRP reinforcement and gradual concrete crushing. This model was developed based on the compatibility of deformation of the partially bonded system and was able to represent the ultimate behavior of the beams well.