Engineering International

Journal Information
EISSN : 2409-3629
Published by: ABC Journals (10.18034)
Total articles ≅ 139

Latest articles in this journal

Saikat Hosen, Ruhul Amin
Published: 1 July 2021
Engineering International, Volume 9, pp 85-100;

Gradient boosting machines, the learning process successively fits fresh prototypes to offer a more precise approximation of the response parameter. The principle notion associated with this algorithm is that a fresh base-learner construct to be extremely correlated with the “negative gradient of the loss function” related to the entire ensemble. The loss function's usefulness can be random, nonetheless, for a clearer understanding of this subject, if the “error function is the model squared-error loss”, then the learning process would end up in sequential error-fitting. This study is aimed at delineating the significance of the gradient boosting algorithm in data management systems. The article will dwell much the significance of gradient boosting algorithm in text classification as well as the limitations of this model. The basic methodology as well as the basic-learning algorithm of the gradient boosting algorithms originally formulated by Friedman, is presented in this study. This may serve as an introduction to gradient boosting algorithms. This article has displayed the approach of gradient boosting algorithms. Both the hypothetical system and the plan choices were depicted and outlined. We have examined all the basic stages of planning a specific demonstration for one’s experimental needs. Elucidation issues have been tended to and displayed as a basic portion of the investigation. The capabilities of the gradient boosting algorithms were examined on a set of real-world down-to-earth applications such as text classification.
Venkata Naga Satya Surendra Chimakurthi
Published: 1 July 2021
Engineering International, Volume 9, pp 129-140;

The study presents the XaaS architecture and explores how this business model has strategically developed and how it has revolutionized the whole business industry. The study indicates how this particular business model allows companies to enhance the range of advantages of Internet Cloud model applications, particularly when it deals with process of media processing and customization of users. Its huge benefits with negligible disadvantages are mentioned as part of the presented research. This study will help to understand the services of XaaS model, challenges experiencing by it and its future opportunities. This will also assists new scholars of field to build a better understanding and better prospects regarding XaaS in future.
Shahadat Hossain, Anwar Hossain, Afm Zainul Abadin, Manik Ahmed
Published: 1 July 2021
Engineering International, Volume 9, pp 73-84;

The recognition of handwritten Bangla digit is providing significant progress on optical character recognition (OCR). It is a very critical task due to the similar pattern and alignment of handwriting digits. With the progress of modern research on optical character recognition, it is reducing the complexity of the classification task by several methods, a few problems encounter during recognition and wait to be solved with simpler methods. The modern emerging field of artificial intelligence is the Deep Neural Network, which promises a solid solution to these few handwritten recognition problems. This paper proposed a fine regulated deep neural network (FRDNN) for the handwritten numeric character recognition problem that uses convolutional neural network (CNN) models with regularization parameters which makes the model generalized by preventing the overfitting. This paper applied Traditional Deep Neural Network (TDNN) and Fine regulated deep neural network (FRDNN) models with a similar layer experienced on BanglaLekha-Isolated databases and the classification accuracies for the two models were 96.25% and 96.99%, respectively over 100 epochs. The network performance of the FRDNN model on the BanglaLekha-Isolated digit dataset was more robust and accurate than the TDNN model and depend on experimentation. Our proposed method is obtained a good recognition accuracy compared with other existing available methods.
Myung Suh Choi, Irene Chon, Katherine Lee, Kevin Kang, Juno Kim, Eddie Bae
Published: 2 April 2021
Engineering International, Volume 9, pp 29-40;

Vulnerable populations, such as patients with mental illnesses, are known to be overly influenced during disasters and pandemics. However, little is known about how people with autism spectrum disorder (ASD), one of the most common neurodevelopmental conditions in the world with a prevalence of 1%, are affected by health-related disasters, particularly the current Covid-19 pandemic. We investigated how individuals with ASD responded to Covid-19 in terms of comprehension and adherence to implemented measures; changes in their behavioral problems; and how the anxiety levels of their caregivers relate to these behavioral changes. Our sample consisted of 50 individuals with ASD (30 male and 20 female; ages ranged from 3 to 14). The majority of our participants had trouble grasping what Covid-19 is and the measurements it necessitates. They also encountered difficulties in implementing pandemic-related social distance and hygiene regulations. During this time, the majority of students stopped receiving special education. In terms of increased stereo-types, aggression, hypersensitivity, behavioral problems, and sleep and appetite changes, we observed a Covid-19-related clinical presentation that resembled PTSD in individuals with ASD. Aberrant Behavior Checklist (ABC) subscales differed significantly before and after the pandemic conditions. There were differences among the caregivers’ anxiety levels between the current behavioral problem levels to the behavioral problem levels prior to the pandemic. The difference in ABC total score, and specifically the lethargy/social withdrawal subscale score, predicted the anxiety score of the parents. Our findings suggest that the Covid-19 period poses unique challenges for people with ASD and their caregivers, emphasizing the importance of targeted, distance special education interventions and other support services for this population.
Ruhul Amin, Siddhartha Vadlamudi
Published: 2 April 2021
Engineering International, Volume 9, pp 41-50;

Cloud data migration is the process of moving data, localhost applications, services, and data to the distributed cloud processing framework. The success of this data migration measure is relying upon a few viewpoints like planning and impact analysis of existing enterprise systems. Quite possibly the most widely recognized process is moving locally stored data in a public cloud computing environment. Cloud migration comes along with both challenges and advantages, so there are different academic research and technical applications on data migration to the cloud that will be discussed throughout this paper. By breaking down the research achievement and application status, we divide the existing migration techniques into three strategies as indicated by the cloud service models essentially. Various processes should be considered for different migration techniques, and various tasks will be included accordingly. The similarities and differences between the migration strategies are examined, and the challenges and future work about data migration to the cloud are proposed. This paper, through a research survey, recognizes the key benefits and challenges of migrating data into the cloud. There are different cloud migration procedures and models recommended to assess the presentation, identifying security requirements, choosing a cloud provider, calculating the expense, and making any essential organizational changes. The results of this research paper can give a roadmap for data migration and can help decision-makers towards a secure and productive migration to a cloud computing environment.
Siddhartha Vadlamudi
Published: 2 April 2021
Engineering International, Volume 9, pp 17-28;

The evolvement of IT has open new doors in connecting many devices to the worldwide web that successively produce data around the physical setting using the IoT. However, the system of message turns out to be slightly intricate in human specialization-internet of things communication for the reason that the IoT is a system including diverse objects transferring data This study examines the hypothetical pathway by which the changes in source attribution that is multiple against single and specialization that is multi-functionality against single functionality of IoT devices affect the quality of human- internet of things interaction. The result from the study obtained from 80 participants that took part in the experiment shows that multiple source attribution improves the condition of information basically for the low-involvement people supports further probes the multiple source effects. However, this study recommends improvement of attribution source and human specialization-IoT.
Meshal Essa, Fahad Salem Alhajri
Published: 2 April 2021
Engineering International, Volume 9, pp 51-60;

Friction stir welding is a modern innovation in the welding processes technology, there are ‎several ways in which this technology has to be investigated in order to refine and make it ‎economically responsible. Aluminum alloys have strong mechanical properties when they are ‎welded by using the Friction Stir welding. Therefore, certain parameters of the welding ‎process need to be examined to achieve the required mechanical properties. In this project, a ‎literature survey has been performed about the friction stir welding process and its parameters ‎for 6xxx series aluminum alloys‎.
S. M. Shahidul Islam, A. A. K. Majumdar
Published: 1 April 2021
Engineering International, Volume 9, pp 9-16;

Recent literature considers the variant of the classical Tower of Hanoi problem with n (³ 1) discs, where r (1 £ r < n) discs are evildoers, each of which can be placed directly on top of a smaller disc any number of times. Letting E(n, r) be the minimum number of moves required to solve the new variant, an explicit form of E(n, r) is available which depends on a positive integer constant N. This study investigates the properties of N.
Apoorva Ganapathy, Adobe Systems
Published: 1 January 2021
Engineering International, Volume 9, pp 61-72;

Quantum Computing in high-frequency trading and fraud detection is an analysis of quantum computing and how it can be used by the different industries especially finance. It is an evolution of computing from the traditional computing method. Quantum computing is a process that is concentrated on creating systems and technology based on quantum theory rules. Quantum theory describes the energy on atomic and subatomic levels. Quantum computing uses quantum bits (qubits) which are more advanced than the traditional bits used by traditional computers. This article focuses on deploying quantum computers in solving problems that cannot be efficiently solved using traditional computers. In the finance sector, such as banking, insurance, and high-frequency trading, quantum computers can help optimize service by providing targeting and predictive analytics to reduce risk, provide personalized customer service, and provide the needed security framework against fraud.
Mani Manavalan
Published: 15 November 2020
Engineering International, Volume 8, pp 139-148;

The most appropriate method to uncover patterns from clinical records for each patient record is to create a bag with a variety of examples in the form of symptoms. The goal of medical diagnosis is to find useful ones first and then map them to one or more diseases. Patients are often represented as vectors in some aspect. Pathologists and dermatopathologists diagnose basal cell carcinomas (BCC), one of the most frequent cutaneous cancers in humans, on a regular basis. Improving histological diagnosis by producing diagnosis ideas, i.e. computer-assisted diagnoses, is a hotly debated research topic aimed at improving safety, quality, and efficiency. Due to their improved performance, machine learning approaches are rapidly being used. Typical images obtained by scanning histological sections, on the other hand, frequently have a resolution insufficient for today's state-of-the-art neural networks. Furthermore, weak labels hamper network training because just a small portion of the image signals the disease class, while the majority of the image is strikingly comparable to the non-disease class. The goal of this work is to see if attention-based deep learning models can detect basal cell carcinomas in histological sections and overcome the ultra-high resolution and poor labeling of full slide images. With an AUC of 0.99, we show that attention-based models can achieve nearly flawless classification performance.
Back to Top Top