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%.

     

Intrusion detection alarms reduction using root cause analysis and clustering

As soon as the Intrusion Detection System (IDS) detects any suspicious activity, it will generate several alarms referring to as security breaches. Unfortunately, the triggered alarms usually are accompanied with huge number of false positives. In this paper, we use root cause analysis to discover the root causes making the IDS triggers these false alarms; most of these root causes are not attacks. Removing the root causes enhances alarms quality in the future. The root cause instigates the IDS to trigger alarms that almost always have similar features. These similar alarms can be clustered together; consequently, we have designed a new clustering technique to group IDS alarms and to produce clusters. Then, each cluster is modeled by a generalized alarm. The generalized alarms related to root causes are converted (by the security analyst) to filters in order to reduce future alarms’ load. The suggested system is a semi-automated system helping the security analyst in specifying the root causes behind these false alarms and in writing accurate filtering rules. The proposed clustering method was verified with three different datasets, and the averaged reduction ratio was about 74% of the total alarms. Application of the new technique to alarms log greatly helps the security analyst in identifying the root causes; and then reduces the alarm load in the future.     

A Hybrid Regularization-Based Multi-Frame Super-Resolution Using Bayesian Framework

The prime purpose for the image reconstruction of a multi-frame super-resolution is to reconstruct a higher-resolution image through incorporating the knowledge obtained from a series of relevant low-resolution images, which is useful in numerous fields. Nevertheless, super-resolution image reconstruction methods are usually damaged by undesirable restorative artifacts, which include blurring distortion, noises, and stair-casing effects. Consequently, it is always challenging to achieve balancing between image smoothness and preservation of the edges inside the image. In this research work, we seek to increase the effectiveness of multi-frame super-resolution image reconstruction by increasing the visual information and improving the automated machine perception, which improves human analysis and interpretation processes. Accordingly, we propose a new approach to the image reconstruction of multi-frame super-resolution, so that it is created through the use of the regularization framework. In the proposed approach, the bilateral edge preserving and bilateral total variation regularizations are employed to approximate a high-resolution image generated from a sequence of corresponding images with low-resolution to protect significant features of an image, including sharp image edges and texture details while preventing artifacts. The experimental results of the synthesized image demonstrate that the new proposed approach has improved efficacy both visually and numerically more than other approaches.     

Stacked Gated Recurrent Unit Classifier with CT Images for Liver Cancer Classification

Liver cancer is one of the major diseases with increased mortality in recent years, across the globe. Manual detection of liver cancer is a tedious and laborious task due to which Computer Aided Diagnosis (CAD) models have been developed to detect the presence of liver cancer accurately and classify its stages. Besides, liver cancer segmentation outcome, using medical images, is employed in the assessment of tumor volume, further treatment plans, and response monitoring. Hence, there is a need exists to develop automated tools for liver cancer detection in a precise manner. With this motivation, the current study introduces an Intelligent Artificial Intelligence with Equilibrium Optimizer based Liver cancer Classification (IAIEO-LCC) model. The proposed IAIEO-LCC technique initially performs Median Filtering (MF)-based pre-processing and data augmentation process. Besides, Kapur’s entropy-based segmentation technique is used to identify the affected regions in liver. Moreover, VGG-19 based feature extractor and Equilibrium Optimizer (EO)-based hyperparameter tuning processes are also involved to derive the feature vectors. At last, Stacked Gated Recurrent Unit (SGRU) classifier is exploited to detect and classify the liver cancer effectively. In order to demonstrate the superiority of the proposed IAIEO-LCC technique in terms of performance, a wide range of simulations was conducted and the results were inspected under different measures. The comparison study results infer that the proposed IAIEO-LCC technique achieved an improved accuracy of 98.52%.     

Foaming properties of oilseed proteins

Oilseeds are important sources of edible proteins. Their varieties varied in oil and protein content; sesame and rapeseeds had the highest oil content, but soybean and glandless cottonseeds had the highest protein content. Foaming properties of oilseed proteins are important for the domestic market to be used in the preparation of various food products. Whole rapeseed had the highest foam capacity followed by soybean, sunflower, safflower, glandless cottonseed, peanut and finally sesame. The extraction of lipids from oilseeds caused a significant improvement in their foam capacity and foam stability. High positive correlation was found between soluble proteins and foam capacity of oilseeds. The foam capacity was high at pH 7, and decreased below it reaching a minimum at pH 4. The foam stability also varied with pH; being maximum at the isoelectric point and minimum at pH 7. The foam capacity of oilseed protein isolates decreased with the prolongation of heating time at 100 °C.     

Prediction of ductile fracture in axisymmetric tension by void coalescence

Fracture strains are predicted for ductile materials undergoing void growth and coalescence. The calculation scheme is based on Gurson–Tvergaard yield function and its associated flow rule. Fracture condition is identified by vanishing stress-carrying capacity of the material. The plastic flow parameters are all determined from experimental evidences for a variety of alloys. Comparison among predicted fracture strains and experimental ones is given for a wide range of conventional and superplastic materials as well as powder compacts. Finally an approximate fracture criterion is proposed.