Rafflesia Khan

Ms. Rafflesia Khan

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2018 in Journal of Image and Graphics
Verified
Journal Article
Closed access
RKRafflesia Khan
Rafflesia Khan
TRTarannum Fariha Raisa
Tarannum Fariha Raisa
RDRameswar Debnath
Rameswar Debnath

8 August 2019 in International Journal of Image, Graphics and Signal Processing
Verified
Journal Article
Open access
PDF file
RKRafflesia Khan
Rafflesia Khan
RDRameswar Debnath
Rameswar Debnath
In this paper, an efficient approach has been proposed to localize every clearly visible object or region of object from an image, using less memory and computing power. For object detection we have processed every input image to overcome several complexities, which are the main limitations to achieve better result, such as overlap between multiple objects, noise in the image background, poor resolution etc. We have also implemented an improved Convolutional Neural Network based classification or recognition algorithm which has proved to provide better performance than baseline works. Combining these two detection and recognition approaches, we have developed a competent multi-class Fruit Detection and Recognition (FDR) model that is very proficient regardless of different limitations such as high and poor image quality, complex background or lightening condition, different fruits of same shape and color, multiple overlapped fruits, existence of non-fruit object in the image and the variety in size, shape, angel and feature of fruit. This proposed FDR model is also capable of detecting every single fruit separately from a set of overlapping fruits. Another major contribution of our FDR model is that it is not a dataset oriented model which works better on only a particular dataset as it has been proved to provide better performance while applying on both real world images (e.g., our own dataset) and several states of art datasets. Nevertheless, taking a number of challenges into consideration, our proposed model is capable of detecting and recognizing fruits from image with a better accuracy and average precision rate of about 0.9875.

8 April 2020 in International Journal of Image, Graphics and Signal Processing
Verified
Journal Article
Closed access
PDF file
RKRafflesia Khan
Rafflesia Khan
RDRameswar Debnath
Rameswar Debnath

23 November 2019
Verified
Conference Paper
Closed access
RKRafflesia Khan
Rafflesia Khan
RDRameswar Debnath
Rameswar Debnath

1 January 2021 in Proceedings of the Institute for System Programming of the RAS
Verified
Journal Article
Open access
PDF file
RKRafflesia Khan
Rafflesia Khan
ASAlexander Schieweck
Alexander Schieweck
CBCiara Breathnach
Ciara Breathnach
Tiziana MargariaTiziana Margaria
Tiziana Margaria
Моделирование считается универсальным подходом к определению и упрощению реальных приложений с помощью соответствующей абстракции. Системная инженерия, управляемая моделями, определяет и объединяет соответствующие концепции, методы и инструменты, которые обеспечивают важные артефакты для междисциплинарной деятельности. В этой статье мы покажем, как мы использовали подход, основанный на моделях, для разработки и улучшения динамического веб-приложения цифровых гуманитарных наук в рамках междисциплинарного проекта, который позволяет студентам-историкам и волонтерам исторических ассоциаций транскрибировать большой корпус изображений документов Управления записью актов гражданского состояния. Наш подход, основанный на моделях, генерирует программное приложение на основе абстрактных моделей данных, рабочего процесса и графического интерфейса пользователя, готовых к развертыванию.

1 February 2019
Verified
Conference Paper
Closed access
RKRafflesia Khan
Rafflesia Khan
With the significant improvement of the deployment of Internet of Things (IoT) into the smart grid infrastructure and the increasing number of connected devices as well as users through the internet, the demand for cyber security is rapidly growing. Which is at the same time producing an acute threat of identity theft, forgery and breach of information security. In order to provide security to every user and device within IoT platform, advance identification and authentication techniques have been investigated by information security users for decades. In this paper, we propose a dynamically configurable connected framework and supporting algorithm which is capable to identify threat and malicious attack through authenticating user or device's identity, controlling service access and establishing trust between object and cloud services. The major contribution of this research work includes a dynamically configurable system framework that is capable of ensuring identification and authentication to every different type of devices within an IoT platform, a scalable system architecture that supports both limited-resource and ensemble devices. Another significant contribution of this work is multi-category security checking that address different aspects of IoT identification and authentication problem. Our proposed system is an application-layer based technology hence, easy to implement and deploy on edge devices and finally we also have presented a comparative discussion with existing approaches.