Mahyudin Ritonga
@umsb.ac.id
Faculty of Islamic Studies
Muhammadiyah University of West Sumatera
RESEARCH INTERESTS
Arabic as Foreign Language
Islamic Studies
Islamic Education
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Mahyudin Ritonga, Manoj L. Bangare, Pushpa Manoj Bangare, Sunil L. Bangare, Seema Sachin Vanjire, Kavita Moholkar, Kishori Kasat, and Purnama Rozak
Institute of Advanced Engineering and Science
In general, the term handwritten character recognition (HCR) refers to the process of recognizing handwritten characters in any form, whereas handwritten text recognition (HTR) refers to the process of reading scanned document images that include text lines and converting those text lines into editable text. The identification of recurring structures and configurations in data is the primary focus of the field of machine learning known as pattern recognition. Optical character recognition, often known as OCR, is a challenging issue to solve when it comes to the field of pattern recognition. This article presents machine learning enabled framework for accurate identification of Arabian handwriting. This framework has provisions for image processing, image segmentation, feature extraction and classification of handwritten images. Images are enhanced using contrast limited adaptive histogram equalization (CLAHE) algorithm. Image segmentation is performed by k-means algorithm. Classification is performed using convolutional neural network (CNN) VGG 16 and support vector machine (SVM) algorithm. Classification accuracy of CNN VGG 16 is 99.33%.
Mahyudin Ritonga, P. Kiran Rao, Khaled A. Z. Alyamani, Mohd Naved, Malik Jawarneh, and Prathipati Ratna Kumar
Springer Nature Switzerland
Sunkara Teena Mrudula, Meenakshi, Mahyudin Ritonga, S. Sivakumar, Malik Jawarneh, Sammy F, T. Keerthika, Kantilal Pitambar Rane, and Bhaskar Roy
Elsevier BV
Uril Bahruddin, Mahyudin Ritonga, Muh. Faruq, and Muhammad Fadli Ramadhan
Institute of Advanced Engineering and Science
Learning Arabic online is faced with several problems, including the ineffective use of learning media. This study aims to describe the tendency of Arabic learners through the Dars Arabi YouTube channel video media, and the relationship between the learner's propensity and the variables of gender, age, and educational background channel users Dars Arabi. This study uses a descriptive statistical method. The sample selection was taken randomly as many as 160 people from a population of around 17,800 YouTube channel subscribers Dars Arabi. This study's findings indicate that the tendency of online Arabic learners is at a moderate average level. This study also shows no statistically significant difference between trends in YouTube channel users and the variables of gender, educational background, and users' age. This study's conclusion shows the importance of using YouTube media in learning Arabic with content that is fun and can be enjoyed by all groups of society in a relaxed manner.
Mahyudin Ritonga, Adam Mudinillah, Eva Ardinal, Tauhid Tauhid, and Talqis Nurdianto
SCAD Independent
The Industrial Revolution era is a time that requires the connection between technology and various aspects of life, including education. But there are still many educational institutions that have not responded well regarding the use of technology in learning, therefore this study aimed to determine the use of E-campus as an online learning media and Arabic learning evaluation media in higher education. The research was conducted at Islamic State University of Batusangkar, the approach used was quantitative with a survey research design. The results of the study stated that E-campus could be used as an alternative in carrying out Arabic language learning, completeness of features, ease of access, and clarity of access as evidence that E-campus was effectively used for online classes in Arabic language learning, until now no features have been found in E-Campus that can be used to evaluate and measure Arabic speaking skills. The utilization of E-campus in Arabic language learning brings great benefits and influences for lecturers and students. The limitation of this study is that researchers did not design an E-campus platform that has complete features to measure four Arabic speaking skills for students, therefore future researchers can conduct research aimed at creating an E-campus model that has more complete features.
Mahyudin Ritonga, Adam Mudinillah, Wasehudin Wasehudin, Julhadi Julhadi, Amrina Amrina and M. Shidqi
Institute of Advanced Engineering and Science
Technology is advancing and developing, and we cannot let go of our lives. One of them is in the world of education, the use of technology is often found. teachers combine technological devices in the learning process so that the learning atmosphere becomes more interesting, not only with increasingly open technological developments and the spread of information and knowledge throughout the world across the boundaries of space and time. Thus, technological developments have a positive impact on educators and students. In this study, researchers measured the extent to which the application of this technology in the learning process was highly valued. For this reason, this research aims to find out the impact of technology on Arabic language learning at the Batusangkar Institute State Islamic University. The method used in this research is a survey research method. Data collection uses observation, interviews and questionnaires. Furthermore, the expected result of this research is to find out the role or influence of technology on Arabic language learning activities in higher education. Based on the research results, it can be seen that there is an influence or influence of technology on Arabic language learning at the Batusangkar State Islamic Institute.
Adiyono Adiyono, Jasiah Jasiah, Mahyudin Ritonga, and Ali Said Al-Matari
Chapman and Hall/CRC
Ritonga Mahyudin, Domenic T. Sanchez, S Teena Mrudula, Ravi Kishore Veluri, Jawarneh Malik, and Abhishek Raghuvanshi
IEEE
The process of taking attendance in the traditional manner is one that is both laborious and time-consuming. Face recognition and identification technology was developed with the primary objective of providing a timesaving automated solution for tracking attendance. This article presents Design of automated smart attendance system using deep learning based face recognition. Camera IoT devices are used to acquire images. These images are stored in cloud via IoT gateway. Images contain many noises. To remove or reduce these noises, adaptive median filter are used. Once noise is removed, then images quality is enhanced by particle swarm optimization. Enhanced images are classified by CNN, CNN VGG 16 and Xception CNN deep learning techniques. Performance is compared on the basis of metrics like- accuracy, specificity and recall. Xception CNN is outperforming other techniques used in the framework. Accuracy, Specificity and Recall rate of Xception CNN is 99.33%, 98.66% and 99.33 percent respectively.
Mahyudin Ritonga, Ahmad Abdulkareem Shaban, Anwar Hammad Al-Rashidi, and Noam Chilani
Springer Science and Business Media LLC
AbstractEvery decision made in the classroom has the potential to either help or hurt a student’s development as a learner. When students’ mental and emotional well-being are taken into account, effective instruction and assessment are possible, despite the importance of learners’ engagement in assessment (LEA), test-taking skills (TTS), self-assessment (SA), learner resilience (LR), and learner autonomy (LA). As a result, this study attempted to illustrate the dynamic between LEA, TTS, SA, LR, and LA. To this end, 435 English as a foreign language (EFL) students at intermediate levels in Afghanistan were given copies of the Test-taking Skills Scale (TTSS), the core of self‑assessments questionnaire (CSAQ), The Academic Resilience Scale (ARS), the learner autonomy questionnaire (LAQ), and the learner engagement in on-line assessment (LEOA). Confirmatory factor analysis (CFA) and structural equation modeling (SEM) screening of the data revealed that resilient EFL students feel better at on-line assessment and in pursuing their objectives. The mediating effects of TTS and SA on LR and LA and consequently Engagement in On-line Assessment were specifically identified. The survey’s ramifications, which may improve language learning and assessment, are reviewed at length.
Kholidah, Muhammad Ridho, Sobhan, and Mahyudin Ritonga
South Florida Publishing LLC
Objective: This study aimed to show the causes of post-divorce violations of women's rights and the implications of religious court decisions on women which violate their rights. This objective is based on the fact that various problems in marriage cause women to sometimes file for legal divorce from their husbands. However, religious court decisions on divorce have violated women's rights, both the right to maintenance and mut'ah.
 
 Theoretical Framework: Divorce and its settlement in religious courts in Indonesia have problems that sometimes disadvantage women.
 
 Method: The research was conducted with a qualitative approach, this is based on the data studied which are facts and documents related to religious courts on divorce. This study used two data collection methods, namely documentation of Religious Court decisions through directories and interviews.
 
 Results and Conclusion: The decision was confirmed to informants through interviews with a number of judges and women as plaintiffs. Based on the results, the Religious Court decision on divorce violating women's rights produces poverty and life stress for women. Women do not get justice because the Religious Court decision creates gender bias. Therefore, it takes courage from judges in deciding divorce cases to realize 3 legal objectives and a legislative review of several articles in Law on Marriage for the reformulation of Islamic Family Law in Indonesia.
 
 Research Implications: The results of the study have implications for changes in religious court decisions on divorce, so that they are no longer detrimental to divorced wives.
 
 Originality/value: Changes in the religious court system towards the problem of divorce are urgently needed, the fulfillment of the rights of wives who are victims of divorce must be the main aspect to be considered by judges.
Mutyalaiah Paricherla, Mahyudin Ritonga, Sandip R. Shinde, Smita M. Chaudhari, Rahmat Linur, and Abhishek Raghuvanshi
Institute of Advanced Engineering and Science
An incursion into the computer network or system in issue occurs whenever there is an attempt made to circumvent the defences that are in place. Training and examination are the two basic components that make up the intrusion detection system (IDS) and each one may be analysed separately. During training, a number of distinct models are built, each of which is able to distinguish between normal and abnormal behaviours that are included within the dataset. This article proposes a combination of ant colony optimization (ACO) and the firefly approach for feature selection. The final outcome of giving careful thought to the selection of features will eventually result in greater accuracy of categorisation. When classifying various sorts of features, we make use of a wide variety of machine learning (ML) algorithms, including AdaBoost, gradient boost, and Bayesian network (BN), amongst others. The tests and assessments made use of data obtained from three distinct datasets, namely NSL-KDD, UNSW-NB15, and CICIDS 2017. The degree of performance of an individual may be broken down into its component parts, which include the F1 score, accuracy, precision, and recall. Gradient boost performs far better when it comes to recognising and classifying incursions.
Mahyudin Ritonga, Armi Gusvita, Romi Saputra, and Meliza Budiarti
AIP Publishing
A. Alfizal, Mahyudin Ritonga, and M. Mafardi
AIP Publishing
Mahyudin Ritonga, Fitria Sartika, Liza Warni, and Umi Hanifah
AIP Publishing
Mahyudin Ritonga, Rosniati Hakim, Talqis Nurdianto, and Apri Wardana Ritonga
Springer Science and Business Media LLC
Ristapawa Indra, Mahyudin Ritonga (Corresponding Author), and Fitrah Santosa
Univ. of Malaya
Differences in views in the first precepts of the Pancasila version of the Jakarta Charter of 22 June 1945 became a genealogical factor that caused some Islamic groups to struggle relentlessly in realizing Islam as the basis of the philosophy and ideology of the state. Part of these groups' movements is compromise and radicalism. Therefore, this research aims to examine non-mainstream Islamic movements in the Indonesian political system. The phenomenological constructivism approach is used in understanding the views of the New Order and the Reform regimes in dealing with non-mainstream Islamic movements, through interview techniques and document analysis. These results showed that radical issues far exceed the normal level of Islamic movements in Indonesia. Furthermore, there is concern that certain groups oriented towards Islamic movements in Indonesia are more co-opted in the anti-Islamic global network sponsored by the United States and the West. The status of the New Order and Reform Regimes did not differ significantly in addressing various state issues related to the Islamic movement. For both regimes, non-mainstream Islamic movements should be strictly controlled. The most effective political instruments to control Islamic nationalist groups whose views differ from secular nationalist in terms of Pancasila as the state ideology are radical issues and terrorism.
Yousef Methkal Abd Algani, Mahyudin Ritonga, B. Kiran Bala, Mohammed Saleh Al Ansari, Malek Badr, and Ahmed I. Taloba
Elsevier BV
Julhadi and Mahyudin Ritonga
International Information and Engineering Technology Association
Franciskus Antonius, Purnachandra Rao Alapati, Mahyudin Ritonga, Indrajit Patra, Yousef A. Baker El-Ebiary, Myagmarsuren Orosoo, and Manikandan Rengarajan
The Science and Information Organization
— The study introduces a comprehensive technique for enhancing the Natural Language Processing (NLP) capabilities of virtual assistant systems. The method addresses the challenges of efficient information transfer and optimizing model size while ensuring improved performance, with a primary focus on model pertaining and distillation. To tackle the issue of vocabulary size affecting model performance, the study employs the SentencePiece tokenizer with unigram settings. This approach allows for the creation of a well-balanced vocabulary, which is essential for striking the right balance between task performance and resource efficiency. a novel pre-layernorm design is introduced, drawing inspiration from models like BERT and RoBERTa. This optimization optimizes the placement of layer normalization within transformer layers during the pretraining phase. Teacher models are effectively trained using masked language modeling objectives and the Deepspeed scaling framework. Modifications to model operations are made, and mixed precision training strategies are explored to ensure stability. The two-stage distillation method efficiently transfers knowledge from teacher models to student models. It begins with an intermediate model, and the data is distilled carefully using logit and hidden layer matching techniques. This information transfer significantly enhances the final student model while maintaining an ideal model size for low-latency applications. In this approach, innovative measurements, such as the precision of filling a mask, are employed to assess the effectiveness and quality of the methods. The findings demonstrate substantial improvements over publicly available models, showcasing the effectiveness of the strategy within complete virtual assistant systems. The proposed approach confirms the potential of the technique to enhance language comprehension and efficiency within virtual assistants, specifically addressing the challenges posed by real-world user inputs. Through extensive testing and rigorous analysis, the capability of the method to meet these objectives is validated.
Miftachul Huda, Abdul Hadi Borham, Azmil Hashim, Mahyudin Ritonga, Mohammad Nabil Almunawar, Muhammad Anshari, Roslee Ahmad, and Hafizul Fahri Hanafi
Springer Nature Switzerland
Miftachul Huda, Ahmad Faizuddin bin Ramli, Mahyudin Ritonga, Mohamad Marzuqi Bin Abdul Rahim, Abd Hadi Borham, Azmil Hashim, Hafizul Fahri Hanafi, and Nor Kalsum Mohd Isa
Routledge
Miftachul Huda, Ahmad Faizuddin bin Ramli, Mahyudin Ritonga, Mohamad Marzuqi Bin Abdul Rahim, Abd Hadi Borham, Azmil Hashim, Husna Husain, and Kalsum Mohd Isa
Routledge