Hirra Anwar

Followers

Following

Public Views

Interests

Uploads

Papers by Hirra Anwar

The NWRD Dataset: An Open-Source Annotated Segmentation Dataset of Diseased Wheat Crop

Sensors

Wheat stripe rust disease (WRD) is extremely detrimental to wheat crop health, and it severely af... more Wheat stripe rust disease (WRD) is extremely detrimental to wheat crop health, and it severely affects the crop yield, increasing the risk of food insecurity. Manual inspection by trained personnel is carried out to inspect the disease spread and extent of damage to wheat fields. However, this is quite inefficient, time-consuming, and laborious, owing to the large area of wheat plantations. Artificial intelligence (AI) and deep learning (DL) offer efficient and accurate solutions to such real-world problems. By analyzing large amounts of data, AI algorithms can identify patterns that are difficult for humans to detect, enabling early disease detection and prevention. However, deep learning models are data-driven, and scarcity of data related to specific crop diseases is one major hindrance in developing models. To overcome this limitation, in this work, we introduce an annotated real-world semantic segmentation dataset named the NUST Wheat Rust Disease (NWRD) dataset. Multileaf imag...

Download

Towards Efficient Aerial Object Detection: Techniques, Datasets and Challenges

2021 International Conference on Communication Technologies (ComTech), 2021

In the past decade, object detection has gained significant attention in computer vision due to v... more In the past decade, object detection has gained significant attention in computer vision due to variety of its applications including picture retrieval, object tracking, self-driving cars, security, activity recognition, traffic surveillance and many more. Latest research in computer vision is making remarkable progress in multiple directions; aerial object detection is one of the foremost. Object detection in natural scenes has been extensively researched however, challenges remain in aerial object detection due to factors such as variation in scale and shape of objects, occlusion, monotonic appearance, and arbitrary orientation of objects in a scene. Literature highlights deep learning models surpass all others in terms of accuracy and efficiency for aerial object detection and recognition. It is well-known that datasets directly impact deep learning models as deep learning itself is a data driven approach. It is therefore crucial to analyze not only the object detection algorithms in aerial imagery, but also the remote sensing datasets that are available. In this paper, we analyze multiple state-of-the-art models that are used in the field of object detection specific to aerial images. We also present a detailed timeline of the prominent aerial imagery datasets; analyze them in detail and present their strengths and weaknesses. At the end, we discuss various challenges present and future research directions in this field. This research work will further pave way for future advancement in the field of aerial object detection and recognition.

Surface Water Pollution Detection using Internet of Things

2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT), 2018

Water is one of the primary requisites and crucial for sustaining the quality of life. In Pakista... more Water is one of the primary requisites and crucial for sustaining the quality of life. In Pakistan its significance is more than ordinary due to the agrarian nature of the economy. Owing to increasing trend in urbanization and industrialization, the quality of water is continuously declining. For this purpose, we propose an Internet of Things (IoT) based water quality system capable of measuring the quality of water in near real time. The proposed solution is based on World Health Organization (WHO) defined water quality metrics. For this purpose, a real time embedded prototype has been developed to record the water quality parameters from the water samples collected from various sources across the study area. The hardware solution sends data to cloud for real time storage and processing. The processed data can be remotely monitored and water flow can be controlled using our developed software solution comprising of mobile app and a dashboard. In addition to water quality monitoring and control system, the predictive analysis of the collected data has been performed. For training purposes a dataset has been obtained from Pakistan Council of Research in Water Resources (PCRWR). Machine learning algorithms have been applied for classification of water quality and the experimental results indicate that deep neural network outperforms all other algorithms with an accuracy of 93%. The preliminary results have shown a high potential of scaling up this concept to an advanced level.

A Very Low Cost, Open, Wireless, Internet of Things (IoT) Air Quality Monitoring Platform

2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT), 2018

Since the recent epidemic rise of smog outbreaks across the country, it has become more crucial t... more Since the recent epidemic rise of smog outbreaks across the country, it has become more crucial than ever to monitor and regulate the quality of air in the atmosphere. The established solutions so far are widely inaccessible for the general public and restricted specifically to organizational use due to high cost and less usability. In this paper we propose a standard solution based on Internet of Things (IoT) technology, which is a cost-effective alternative to traditional air quality monitoring systems. To realize this cost effectiveness, we have used NodeMCU system on chip which is a low cost, low energy, open, wireless LAN platform. Through the proposed solution, we demonstrate air quality monitoring by collecting data using temperature, humidity, carbon monoxide and nitrogen dioxide sensors and subsequently performed data analysis to infer the relationship of pollutant gases with weather parameters influencing the air quality. Through this research we support the concept of "Going Green" to sustain healthy, and cleaner environment for current and future generations.

Download

Corrigendum: Water Supply 20 (1), 28–45: Water quality monitoring: from conventional to emerging technologies, Umair Ahmed et al

Water Supply, 2020

Download

Efficient Water Quality Prediction Using Supervised Machine Learning

Water, 2019

Water makes up about 70% of the earth’s surface and is one of the most important sources vital to... more Water makes up about 70% of the earth’s surface and is one of the most important sources vital to sustaining life. Rapid urbanization and industrialization have led to a deterioration of water quality at an alarming rate, resulting in harrowing diseases. Water quality has been conventionally estimated through expensive and time-consuming lab and statistical analyses, which render the contemporary notion of real-time monitoring moot. The alarming consequences of poor water quality necessitate an alternative method, which is quicker and inexpensive. With this motivation, this research explores a series of supervised machine learning algorithms to estimate the water quality index (WQI), which is a singular index to describe the general quality of water, and the water quality class (WQC), which is a distinctive class defined on the basis of the WQI. The proposed methodology employs four input parameters, namely, temperature, turbidity, pH and total dissolved solids. Of all the employed ...

Download

Water quality monitoring: from conventional to emerging technologies

Water Supply, 2019

The rapid urbanization and industrial development have resulted in water contamination and water ... more The rapid urbanization and industrial development have resulted in water contamination and water quality deterioration at an alarming rate, deeming its quick, inexpensive and accurate detection imperative. Conventional methods to measure water quality are lengthy, expensive and inefficient, including the manual analysis process carried out in a laboratory. The research work in this paper focuses on the problem from various perspectives, including the traditional methods of determining water quality to gain insight into the problem and the analysis of state-of-the-art technologies, including Internet of Things (IoT) and machine learning techniques to address water quality. After analyzing the currently available solutions, this paper proposes an IoT-based low-cost system employing machine learning techniques to monitor water quality in real time, analyze water quality trends and detect anomalous events such as intentional contamination of water.

Download

Self-adaptive access control & delegation in cloud computing

2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2016

Cloud computing has seen significant progress in the last decade, and is still on the rise. A big... more Cloud computing has seen significant progress in the last decade, and is still on the rise. A big number of companies are shifting their infrastructure to the cloud because of the numerous advantages it offers, such as rapid elasticity and scalability. However, moving to the cloud also presents a number of challenges. In this paper we focus on one of the major challenges, i.e., access control and delegation in a cloud environment. There exist many frameworks and models that solve issues pertinent to this area and allow dynamic delegation of access rights. However, none of them are robust enough to handle unprecedented changes, i.e., situations not handled at the time of requirements engineering. We've presented a risk-based, self-adaptive access control and delegation framework that caters to such situations by continuously monitoring and evaluating the user risk score and environmental factors, and automatically adapting to the changes incurred by reconfiguring the system. The proposed framework is able to adapt to unprecedented change as it can delegate access rights to previously unauthorized users in an emergency situation and revoke users' access rights based on environmental factors, while running in a continuous feedback loop.

Self adaptations in access control models in context of cloud computing

2015 Conference on Information Assurance and Cyber Security (CIACS), 2015

Access control models are widely adopted by IT industry as they restrict access to the digital da... more Access control models are widely adopted by IT industry as they restrict access to the digital data and resources. While different access control models have been presented in literature, there is an issue which has not been investigated so far i.e. the need for self-adaptation in access control models in distributed computing environment. We have presented in-depth analysis, which demonstrates that the existing traditional and non-traditional access control models are unable to cope up with the challenges of dynamic adaptations in the system due to unprecedented changes which are not identified at requirement engineering time. Due to runtime changes either in the operational environment of a system or in user requirements, system changes its behaviour dynamically. Hence for a system that has been deployed in cloud computing environment where user requirements change dynamically, a useful access control model is the one that can handle the authorization requests along with the runtime changes in the system. This paper presents the analysis of various access control models and frameworks in order to demonstrate the need of self-adaptation in access control models particularly in the domain of cloud computing.

Federated Identity Management (FIM): Challenges and opportunities

2015 Conference on Information Assurance and Cyber Security (CIACS), 2015

Federated Identity Management (FIM) is a method that facilitates management of identity processes... more Federated Identity Management (FIM) is a method that facilitates management of identity processes and policies among the collaborating entities. It also enables secure resource sharing among these entities, but it hasn't been as widely adopted as expected. So, in this paper we have identified factors that are pivotal for a holistic FIM framework or model. These factors include trust management and trust establishment techniques, preservation of user privacy, consistent access rights across Circles of Trust (CoTs), continuous monitoring of collaborating entities and adaptation to unanticipated events. On the basis of these factors, we have presented an extensive comparative analysis on existing FIM frameworks and models that identify current challenges and areas of improvement in this field. We've also analyzed these frameworks and models against a set of attacks to gauge their strengths and weaknesses.

An Extensible Identity Management Framework for Cloud-Based E-Government Systems

Cloud Computing Technologies for Connected Government

Numerous Cloud Identity Management (IdM) systems have been designed and implemented to meet the d... more Numerous Cloud Identity Management (IdM) systems have been designed and implemented to meet the diverse functional and security requirements of various organizations. These requirements are subjective in nature; for instance, some government organizations require security more than efficiency while others prioritize performance and immediate response over security. However, most of the existing IdM systems are incapable of handling the user-centricity, security & technology requirements and are also domain specific. In this regard, this chapter elaborates the need to use Cloud Computing technology for enhancing the effectiveness and transparency of IdM functions and presents a comprehensive and well-structured Extensible IdM Framework for Cloud based e-government institutions. We present the design and implementation details of the proposed framework, followed by a case study which shows how government organizations of Pakistan would use the proposed framework to improve their IdM processes and achieve diverse IdM services.

Download

Attribute based access control in DSpace

ABSTRACT Authorization is an important security aspect that needs to be taken care of when access... more ABSTRACT Authorization is an important security aspect that needs to be taken care of when access on sensitive resources has to be restricted. In Institutional Digital Repository Systems, controlled and protected access on digital content is ensured through flexible yet effective access control mechanisms. Repositories today store digital content of varying security levels and access on such content requires context and environment to be considered as well to make an access control decision. Fine grained authorization which elaborates context aware constraints is suitable for restricting access in such systems. Attribute based access control (ABAC) model relies on attributes as the basic unit of access and provides a fine grained level authorization. In this paper we improve the primitive authorization of DSpace Institutional Digital Repository System by incorporating Attribute based access control.

PISA: Improving the pseudo-randomness of the pen-and-paper cipher based on the Solitaire algorithm

2012 15th International Multitopic Conference (INMIC), 2012

ABSTRACT

Comparative Analysis of Group Centric Access Control Models

Communications in Computer and Information Science, 2012

Digital information is one of the sensitive resources in any organization that needs to be well p... more Digital information is one of the sensitive resources in any organization that needs to be well protected and secured to avoid unauthorized access and consequently its misuse. In a group centric environment dynamic sharing of resources takes place within an authorized group of users for a specific purpose. Security of shared resources becomes more important and challenging in a group-centric environment. Different organizations comprise of a complex structure in which multiple groups exist at a time and access rights are provisioned and delegated within groups. Groups are created and disassembled dynamically based on events or tasks required. These complex structures need to be managed and secured and we need effective provisioning of access control and delegation of access rights within these groups. We present a comparative study of the access control models in group-centric environment and discuss the open research areas in group centric environment.

The NWRD Dataset: An Open-Source Annotated Segmentation Dataset of Diseased Wheat Crop

Sensors

Download

Towards Efficient Aerial Object Detection: Techniques, Datasets and Challenges

2021 International Conference on Communication Technologies (ComTech), 2021

Surface Water Pollution Detection using Internet of Things

2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT), 2018

A Very Low Cost, Open, Wireless, Internet of Things (IoT) Air Quality Monitoring Platform

2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT), 2018

Download

Corrigendum: Water Supply 20 (1), 28–45: Water quality monitoring: from conventional to emerging technologies, Umair Ahmed et al

Water Supply, 2020

Download

Efficient Water Quality Prediction Using Supervised Machine Learning

Water, 2019

Download

Water quality monitoring: from conventional to emerging technologies

Water Supply, 2019

Download

Self-adaptive access control & delegation in cloud computing

2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2016

Self adaptations in access control models in context of cloud computing

2015 Conference on Information Assurance and Cyber Security (CIACS), 2015

Federated Identity Management (FIM): Challenges and opportunities

2015 Conference on Information Assurance and Cyber Security (CIACS), 2015

An Extensible Identity Management Framework for Cloud-Based E-Government Systems

Cloud Computing Technologies for Connected Government

Download

Attribute based access control in DSpace

PISA: Improving the pseudo-randomness of the pen-and-paper cipher based on the Solitaire algorithm

2012 15th International Multitopic Conference (INMIC), 2012

ABSTRACT

Comparative Analysis of Group Centric Access Control Models

Communications in Computer and Information Science, 2012

Hirra Anwar

Uploads

Papers by Hirra Anwar

Log In