Abstract Affective computing, a subcategory of artificial intelligence, detects, processes, interprets, and mimics human emotions. Thanks to the continued advancement of portable non-invasive human sensor technologies, like brain–computer interfaces (BCI), emotion recognition has piqued the interest of academics from a variety of domains. Facial expressions, speech, behavior (gesture/posture), and physiological signals can all be used to identify human emotions. However, the first three may be ineffectual because people may hide their true emotions consciously or unconsciously (so-called social masking). Physiological signals can provide more accurate and objective emotion recognition. Electroencephalogram (EEG) signals respond in real time and are more sensitive to changes in affective states than peripheral neurophysiological signals. Thus, EEG signals can reveal important features of emotional states. Recently, several EEG-based BCI emotion recognition techniques have been developed. In addition, rapid advances in machine and deep learning have enabled machines or computers to understand, recognize, and analyze emotions. This study reviews emotion recognition methods that rely on multi-channel EEG signal-based BCIs and provides an overview of what has been accomplished in this area. It also provides an overview of the datasets and methods used to elicit emotional states. According to the usual emotional recognition pathway, we review various EEG feature extraction, feature selection/reduction, machine learning methods (e.g., k-nearest neighbor), support vector machine, decision tree, artificial neural network, random forest, and naive Bayes) and deep learning methods (e.g., convolutional and recurrent neural networks with long short term memory). In addition, EEG rhythms that are strongly linked to emotions as well as the relationship between distinct brain areas and emotions are discussed. We also discuss several human emotion recognition studies, published between 2015 and 2021, that use EEG data and compare different machine and deep learning algorithms. Finally, this review suggests several challenges and future research directions in the recognition and classification of human emotional states using EEG. 

/pdf/human-emotion-recognition-from-eeg-based-brain-computer-3ewpz51o.pdf

Human emotion recognition from EEG-based brain–computer interface using machine learning: a comprehensive review

Recognition of cursive handwritten Arabic text is a difficult problem because of context-sensitive character shapes, the non-uniform spacing between words and within a word, diverse placements of dots, and diacritics, and very low inter-class variation among individual classes. In this paper, we review and investigate different deep learning architectures and modeling choices for Arabic handwriting recognition. Further, we address the problem that imbalanced data sets present to deep learning systems. In order to address this issue, we are presenting a novel adaptive data-augmentation algorithm to promote class diversity. This algorithm assigns a weight to each word in the database lexicon. This weight is calculated based on the average probability of each class in a word. Experimental results on the IFN/ENIT and AHDB databases have shown that our presented approach yields state-of-the-art results.

/pdf/exploring-deep-learning-approaches-to-recognize-handwritten-2z8332hael.pdf

Exploring Deep Learning Approaches to Recognize Handwritten Arabic Texts

Extending technologies and data development culminated in the need for quicker and more reliable processing of massive data sets. Machine Learning techniques are used excessively. This paper, therefore, attempts to deal with data processing, using a support vector machine (SVM) algorithm in different fields since it is a reliable, efficient classification method in the area of machine learning. Accordingly, many works have been explored in this paper to cover the use of SVM classifier. Classification based on SVM has been used in many fields like face recognition, diseases diagnostics, text recognition, sentiment analysis, plant disease identification and intrusion detection system for network security application. Based on this study, it can be concluded that SVM classifier has obtained high accuracy results in most of the applications, specifically, for face recognition and diseases identification applications. Keywords—ML, Classification, SVM, Applications.

/pdf/machine-learning-applications-based-on-svm-classification-a-2myfaz80q8.pdf

Machine Learning Applications based on SVM Classification A Review

The main aspect of database protection is to prove the ownership of data that describes who is the originator of data. It is of particular importance in the case of electronic data, as data sets are often modified and copied without proper citation or acknowledgement of originating data set. We present a novel method for watermarking relational databases for identification and proof of ownership based on the secure embedding of blind and multi-bit watermarks using Bacterial Foraging Algorithm (BFA). Feasibility of BFA implementation is shown in the framed watermarking databases application. Identification of owner is cryptographically made secure and used as an embedded watermark. An improved hash partitioning approach is used that is independent of primary key of the database to secure ordering of the tuples. Strength of BFA is explored to make the technique robust, secure and imperceptible. BFA is implemented to give nearly global optimal values bounded by data usability constraints and thus makes database fragile to any attack. The parameters of BFA are tuned to reduce the execution time. BFA is experimentally proved to be better solution than Genetic Algorithm (GA). The technique proposed is experimentally proved to be resilient against malicious attacks.

Watermarking relational databases using bacterial foraging algorithm

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%.

Recognizing arabic handwritten characters using deep learning and genetic algorithms

Offline Arabic handwritten recognition lies in a major field of challenge due to the changing styles of writing from one individual to another. It is difficult to recognize the Arabic handwritten because of the same appearance of the different characters.  In this paper a proposed method for Offline Arabic handwritten recognition. The   proposed method for recognition hand-written Arabic word without segmentation to sub letters based on feature extraction scale invariant feature transform (SIFT) and   support vector machines (SVMs) to enhance the recognition accuracy. The proposed method  experimented using (AHDB) database. The experiment result  show  (99.08) recognition  rate.

Arabic Handwriting Word Recognition Based on Scale Invariant Feature Transform and Support Vector Machine

Providing ownership on relational database is a cru cial issue in today internet-based application environments and in many content distribution applications.This paper provides the effective wate rmarking technique to protect valuable numeric relational data from illegal dupli cations and redistributions as well as to claim ownership,the robustness of propos ed system depending on using new hybrid techniques ,first technique MAC(Message Authentication Code) that used one way hash function SHA1 ,second technique is threshold generator base on simple combination of odd number of register an d by using secret key in proposed system. Detecting the watermark neither re quires access to neither the original data nor the watermark. The watermark can be detected even in a small subset of a watermarked relation as long as the sam ple contains some of the marks. The finally stage is the analysis of technique that used, our extensive analysis shows that the proposed technique is robust against various forms of malicious attacks and updates to the data.

/pdf/watermarking-for-relational-database-by-using-threshold-2rpfqvj4lj.pdf

Watermarking for Relational Database by using Threshold Generator

In a writer recognition system, the system performs a “one-to-many” search in a large database with handwriting samples of known authors and returns a possible candidate list. This paper proposes method for writer identification handwritten Arabic word without segmentation to sub letters based on feature extraction speed up robust feature transform (SURF) and K nearest neighbor classification (KNN) to enhance the writer's  identification accuracy. After feature extraction, it can be cluster by K-means algorithm to standardize the number of features. The feature extraction and feature clustering called to gather Bag of Word (BOW); it converts arbitrary number of image feature to uniform length feature vector. The proposed method experimented using (IFN/ENIT) database. The recognition rate of experiment result is (96.666).

/pdf/writer-identification-based-on-arabic-handwriting-2jg3n76y90.pdf

Writer Identification Based on Arabic Handwriting Recognition by using Speed Up Robust Feature and K- Nearest Neighbor Classification

In this paper, a proposed method to authentication system based on a hand writing recognition without segmentation to sub letters based on feature extraction Speed Up Robust Features (SURF) and Support Vector Machine (SVM) to enhance the accuracy. After feature extraction, the result can be clustered by using the K-means algorithm to standardize the number of features. These two operations together (feature extraction and feature clustering) called Bag of Word (BOW). It converts the arbitrary number of image features to uniform length features vector. The proposed method experimented using two databases; the standard (IFN/ENIT) database and the proposed database consist of 30 different writers with 70 margins images. The proposed system achieves (96.67%) recognition rate for IFN/IENT database.

Authentication System Based on Hand Writing Recognition

Social networking sites such as Facebook, Twitter, Instagram, and Chat are stronger communication tools. Users use multiple social network applications for different purposes such as business or communications and multiple accounts in different social network applications for each user. In order to identify the same user in an accurate method is important in many services. In this paper, we proposed an algorithm to identify users based on check-in and profile matching using fuzzy matching method in profile and Bayesian algorithm in check-in. This method called “Profile Matching and Check-in” PMC. The proposed method simulated using Python programming language version (2.7) for the Gowalla dataset, the accuracy of the proposed method is 84%. This method achieves high security and privacy to the system.

Bashar Saadoon Mahdi

Papers

Arabic Handwriting Word Recognition Based on Scale Invariant Feature Transform and Support Vector Machine

Watermarking for Relational Database by using Threshold Generator

Writer Identification Based on Arabic Handwriting Recognition by using Speed Up Robust Feature and K- Nearest Neighbor Classification

Authentication System Based on Hand Writing Recognition

Proposed User Identification Algorithm Across Social Network Using Hybrid Techniques