Arabic Handwriting Classification using Deep Transfer Learning Techniques

Arabic handwriting is slightly different from the handwriting of other languages; hence it is possible to distinguish the handwriting written by the native or non-native writer based on their handwriting. However, classifying Arabic handwriting is challenging using traditional text recognition algorithms. Thus, this study evaluated and validated the utilisation of deep transfer learning models to overcome such issues. Hence, seven types of deep learning transfer models, namely the AlexNet, GoogleNet, ResNet18, ResNet50, ResNet101, VGG16, and VGG19, were used to determine the most suitable model for classifying the handwritten images written by the native or non-native. Two datasets comprised of Arabic handwriting images were used to evaluate and validate the newly developed deep learning models used to classify each model’s output as either native or foreign (non-native) writers. The training and validation sets were conducted using both original and augmented datasets. Results showed that the highest accuracy is using the GoogleNet deep learning model for both normal and augmented datasets, with the highest accuracy attained as 93.2% using normal data and 95.5% using augmented data in classifying the native handwriting.

Recognition of Human Face Regions under Adverse Conditions—Face Masks and Glasses—In Thermographic Sanitary Barriers through Learning Transfer from an Object Detector

The COVID-19 pandemic has detrimentally affected people’s lives and the economies of many countries, causing disruption in the health, education, transport, and other sectors. Several countries have implemented sanitary barriers at airports, bus and train stations, company gates, and other shared spaces to detect patients with viral symptoms in an effort to contain the spread of the disease. As fever is one of the most recurrent disease symptoms, the demand for devices that measure skin (body surface) temperature has increased. The thermal imaging camera, also known as a thermal imager, is one such device used to measure temperature. It employs a technology known as infrared thermography and is a noninvasive, fast, and objective tool. This study employed machine learning transfer using You Only Look Once (YOLO) to detect the hottest temperatures in the regions of interest (ROIs) of the human face in thermographic images, allowing the identification of a febrile state in humans. The algorithms detect areas of interest in the thermographic images, such as the eyes, forehead, and ears, before analyzing the temperatures in these regions. The developed software achieved excellent performance in detecting the established areas of interest, adequately indicating the maximum temperature within each region of interest, and correctly choosing the maximum temperature among them.

Investigating the Effective Climate on Transfer of Lessons Learned and Providing Solutions to Improve the Effectiveness of HSE Training Courses

Background: Today's businesses spend a lot of money on educating their personnel. What matters is that people use their knowledge to their jobs. The goal of this study was to look into the environment that affects learning transfer and come up with a solution to increase the effectiveness of health, safety and environment (HSE) courses. Methods: In 2020, a cross-sectional study was done at the Tehran Oil Refining Company. The number of samples was 200, according to Cochran's formula. The major data gathering technique was a 20-item questionnaire created by the researcher. The multivariate regression model was used to analyze the study data, which was done with IBM SPSS software. Results: The questionnaire's content validity and reliability were estimated to be 0.83 and 0.929, respectively. 3.68±0.22 was the atmospheric indicator that proved effective in transferring learning and providing a way to increase the effectiveness of HSE training. The climate index affecting the transfer of learning had a significant link with the parameters of work experience (p = 0.02), education.(p = 0.03), and kind of employment (P = 0.01), according to the results of linear multivariate regression analysis. Conclusion: The atmospheric index influencing learning transfer and proposing a solution to increase the efficacy of HSE courses in the Tehran Oil Refining Company was deemed favorable. The outcomes of this study revealed that supervisors on job units in this business provide a supportive environment that is perfectly aligned with encouraging learners to enroll in training courses.

Transfer learning-based Fashion Image Classification using Hybrid 2D-CNN and ImageNet Neural Network

Many algorithms have been developed as a result of recent advances in machine learning to handle a variety of challenges. In recent years, the most popular transfer learning method has allowed researchers and engineers to run experiments with minimal computing and time resources. To tackle the challenges of classification, product identification, product suggestion, and picture-based search, this research proposed a transfer learning strategy for Fashion image classification based on hybrid 2D-CNN pretrained by VGG-16 and AlexNet. Pre-processing, feature extraction, and classification are the three parts of the proposed system's implementation. We used the Fashion MNIST dataset, which consists of 50,000 fashion photos that have been classified. Training and validation datasets have been separated. In comparison to other conventional methodologies, the suggested transfer learning approach has higher training and validation accuracy and reduced loss. Keywords: Machine Learning, Transfer Learning, Convolutional Neural Network, Image Classification, VGG16, AlexNet, 2D CNN.

impact of a smartphone or tablet application on learning transfer in the field of continuing vocational training

The study aimed to research the impacts of a smartphone or tablet application in the field of continuing vocational training(CVT). Well trained employees are of utmost importance in the eyes of any corporation. With the help of literature review and survey, the empirical study gets to conclude that these modes help proactively to increase learning transfer in CVT. Furthermore, the study shows that such applications are currently not yet a standard learning transfer tool.

Validating and Testing Learning Transfer System Inventory (LTSI) in a Developing Country Context: A Case of Pakistan’s Service Sector

Learning Transfer System Inventory (LTSI) is a tool used to measure the impact of various factors on learning outcomes. The objective of the study was to understand the problems faced by Pakistan service sector employees and finally to evaluate the impact of motivation scale, environment scale and trainee ability scale on outcome scale.Questionnaire of Learning Transfer System Inventory adopted from Holton, Bates and Ruona (2000) was used.569 questionnaires were administered to the employees of Peshawar service sector including employees of banks, non-government organizations, education and health sectors, out of which 415 were completed with a response rate of 73%.Correlation analysis shows that value of R is 0.969 that means there is 96.9% correlation in variables that are considered in model. The value of R Square is 0.939. In Service Sector, Supervisor Sanction Variable, Performance Outcome Expectation Variable and Performance Coaching Variable are insignificant and do not bring change in our dependent variable Outcome. Standardized Coefficients show that Personal Capacity for Transfer Variable, Peer Support Variable, Supervisor Support Variable and Transfer Effort Performance Expectation Variable having higher Standardized Coefficients betas, that means those variables bring greater change in dependent variable Outcome.

Assessing learning transfer and constraining issues in EAP writing practices

The aim of this study was to investigate what learners carry over from a general academic writing course to disciplinary writing settings and the variables constraining the quality of the outcome. Seven EFL university writing teachers and 58 students were selected using purposive and stratified sampling techniques. Data were generated using in-depth interview and document analysis. Thematic analysis and non-parametric statistical tools were employed to analyze the data. The findings showed that the students made limited learning transfer from the writing course to their writing settings across academic discourses. While surface level knowledge of grammatical features show better transfer, skills of discourse level writing processes, thinking strategies and vocabulary showed very poor transfer. A number of reasons are identified for the failure of learning transfer in the study setting. Among others, EAP teachers’ failure to bridge the EFL writing and content area writing practice contributed to this problem. The other variable causing this problem is students’ failure to make significant moves to adapt skills of writing processes and thinking strategies to new situations. Based on these evidences, alternative ways of improving the carryover impact of such courses have been put forward.