2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS), 2019
Edge Detection in image processing is very important due to large number of applications it offer... more Edge Detection in image processing is very important due to large number of applications it offers in variety of fields that extend from medical imaging to text and object detection, security, mapping of roads, real time traffic management, image inpainting, video surveillance and many more. Traditional methods for edge detection mostly rely on gradient filter based algorithms which usually require excessive pre-processing of the images for noise reduction and post-processing of the generated results in order to get fine edges. Moreover, traditional algorithms are not reliable generally because as the noise in images increases their efficiency is affected largely due to increase of mask size which also makes the system computationally expensive. In this paper, we will employ CNN method to detect edges of roof images. Incorporating CNN into edge detection problem makes the whole system simple, fast, and reliable. Moreover, with no more extra training and without additional feature ex...
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), 2016
Macular retinal anomaly known as Drusen present in the eyes infected with Age Macular Degeneratio... more Macular retinal anomaly known as Drusen present in the eyes infected with Age Macular Degeneration (AMD) can be visualized with optical coherence tomography (OCT). This paper presents an algorithm to automatically segment retinal pigment epithelium (RPE) layer of an eye using spectral domain optical coherence tomography (SD-OCT) images for the detection of drusen. Segmentation framework is based on intensity level thresholding of high reflective pixels around retinal nerve fiber layer (RNFL). A dataset of 50 different B-scan is taken with having 25 AMD and 25 heathy images. Bottom layer of the retina known as RPE layer is extracted and analyzed by fitting a second order polynomial curve. The difference between both the curvess decide the class of the image. Results show an accurate detection of drusen with 96 % accuracy.
2021 IEEE 7th International Conference on Network Softwarization (NetSoft), 2021
Intent-Based Networking (IBN) is a model that enables proactive network control and automation to... more Intent-Based Networking (IBN) is a model that enables proactive network control and automation to satisfy high-level demands. It follows a closed-loop mechanism that abstracts the network complexity and dynamically allows updates to the network monitoring and intelligence. Hence, it eliminates the traditionally practiced error-prone manual network control. In contrast with the traditional reactive approach, IBN-based approach promotes the proactive and dynamic solution. To this end, IBN uses machine learning (ML) to predict the future and keeps a balance between the intended and actual state. Hence, this work considers an IBN-driven routing mechanism to ensure service provisioning with the desired quality of service (QoS). In contrast to the traditional static routing scheme, this work considers AI-driven dynamic and proactively updatable routing schemes to ensure QoS. This work demonstrates AI-driven service route control mechanism for ensuring quality of service (QoS) on top of Ko...
On-demand service is the main feature of the 5G network, and Network Function Virtualization (NFV... more On-demand service is the main feature of the 5G network, and Network Function Virtualization (NFV) provides it by virtualizing the existing 5G network infrastructure. NFV crafts various virtual networks on a shared physical network, but one of the core challenges in future 5G networks is to automate the modeling of Virtualized Network Functions (VNFs) and end-to-end Network Service (NS) orchestration with less human interaction. Traditionally, the descriptor of VNF and NS is created manually, which requires expert-level skills. This manual approach has a big threat of human error, which can be avoided by using the Intent-Based Networking (IBN) approach. The IBN approach eliminates the requirement of expertise for designing VNFs and NS by taking users’ intentions as an input. In this paper, the proposed system presents the Intent Management System for VNF modeling and end-to-end NS orchestration for multi-platforms. This system takes the high-level information related to a specific s...
The fifth-generation mobile network presents a wide range of services which have different requir... more The fifth-generation mobile network presents a wide range of services which have different requirements in terms of performance, bandwidth, reliability, and latency. The legacy networks are not capable to handle these diverse services with the same physical infrastructure. In this way, network virtualization presents a reliable solution named network slicing that supports service heterogeneity and provides differentiated resources to each service. Network slicing enables network operators to create multiple logical networks over a common physical infrastructure. In this research article, we have designed and implemented an intent-based network slicing system that can slice and manage the core network and radio access network (RAN) resources efficiently. It is an automated system, where users just need to provide higher-level network configurations in the form of intents/contracts for a network slice, and in return, our system deploys and configures the requested resources accordingl...
By the prediction of future location for a vehicle in Internet of Vehicles (IoV), data forwarding... more By the prediction of future location for a vehicle in Internet of Vehicles (IoV), data forwarding schemes can be further improved. Major parameters for vehicle position prediction includes traffic density, motion, road conditions, and vehicle current position. In this paper, therefore, our proposed system enforces the accurate prediction with the help of realtime traffic from the vehicles. In addition, the proposed Neural Network Model assists Edge Controller and centralized controller to compute and predict vehicle future position inside and outside of the vicinity, respectively. Last but not least, in order to get real-time data, and to maintain a quality of experience, the edge controller is explored with Software Defined Internet of Vehicles. In order to evaluate our framework, SUMO simulator with Open Street map is considered and the results prove the importance of vehicle position prediction for vehicular networks. Index Terms-Vehicle to Anything (V2X), position prediction, SDN, edge controllers, internet of vehicles, GIS, neural network I. INTRODUCTION Nowadays, vehicles on the road are increasing exponentially and it is expected that the count will go beyond 2.5 billion by 2050s [1]. With the exponential growth of traffic, the complexity of traffic management propagates in parallel. Intelligent Transportation System (ITS) is hot research among the autonomous industry with its varying road safety and entertainment applications [2]. The study of the connected car is one of the key research area and is being evolved under the umbrella of the Internet of Vehicles (IoV) [3], [4], a subfield of Internet of Things (IoT). The main focus of IoV is V2X communication, i.e. vehicle to everything (vehicle to infrastructure, vehicle, pedestrians, network gateways, and RSUs communication, etc. [5], [6]). V2X communication is considered as one of the vital technology explored by ITS for traffic assistance in a smart city. V2X communication consists of Dedicated Short Range Communications (DSRC) or cellular infrastructure, based on its requirement to their respective scenarios. However, a combination of both the technologies can also deliver promising results with high throughput and low latency for critical applications [7]. [8].
Container-based service orchestration is getting famous increasingly because of its ability to be... more Container-based service orchestration is getting famous increasingly because of its ability to be deployed quickly and it is cheaper as well as more reliable when compared to virtual machines. Leveraging the container characteristic, deployment of 5G modules as a group of containers on different nodes is an excellent solution to construct a 5g system. In a 5G system, network slicing plays a vital role to isolate the on-demand services and the SDN based overlay network consisting of containers provides the platform which manages to slice the network using intent-based networking. As the number of containers in a deployment increases on hosts across the overlay network with the passage of time in the 5G network, therefore it is necessary to manage them with the tool in a straight way with high-level abstraction. In this paper, we present the deployment of an overlay network which consists of Kubernetes nodes and Open vSwitch. In this paper, we also present the intent-based slicing system using Software Defined Network controller and an Intent-Based Networking (IBN) Manager among the containers across the Kubernetes pods in an overlay network. Index Terms-Containers, kubernetes, software-defined network, slicing, intent-based networking, overlay networking Wang-Cheol Song work at the Computer Engineering department, Jeju National University, South Korea. Member of Advanced Network Forum (correspondent), Korea Contents Association (correspondent Distinguished Service medal 2005), Korea Information Science Society (correspondent), Korean Institute Communications and Sciences (correspondent). He received B.S. degree in Food Engineering and Electronics
International Journal of Modern Education and Computer Science, 2013
In Project management, team's motivation is one of the most important factors in the success of a... more In Project management, team's motivation is one of the most important factors in the success of a project. Project Managersmanage the whole project by assuring that all the members are performing the duties they are assigned. Emotional Intelligence is the ability to identify the attitude of a team member towards a project. In developing countrieslack of emotional intelligence factors may cost people their jobs. In this paper conflict management, technical management, interest development and stress management problems are discussed with reference to developing countries and an efficient approach to resolve these issues is also proposed. Therefore project managers should raise their EI (emotional intelligence) and also help members to raise their EI. This paper explores the related work in EI, and then finds the useful Emotional Intelligence factors which are appropriate for the project manager. Then this paper also determinesa framework which is useful for project managers.
Requirement engineering is an essence of software development life cycle. The more time we spend ... more Requirement engineering is an essence of software development life cycle. The more time we spend on requirement engineering, higher the probability of success. Effective requirement engineering ensures and predicts successful software product. This paper presents the adaptation of requirement engineering practices in small and medium size companies of Pakistan. The study is conducted by questionnaires to show how much of requirement engineering models and practices are followed in Pakistan.
2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS), 2019
Edge Detection in image processing is very important due to large number of applications it offer... more Edge Detection in image processing is very important due to large number of applications it offers in variety of fields that extend from medical imaging to text and object detection, security, mapping of roads, real time traffic management, image inpainting, video surveillance and many more. Traditional methods for edge detection mostly rely on gradient filter based algorithms which usually require excessive pre-processing of the images for noise reduction and post-processing of the generated results in order to get fine edges. Moreover, traditional algorithms are not reliable generally because as the noise in images increases their efficiency is affected largely due to increase of mask size which also makes the system computationally expensive. In this paper, we will employ CNN method to detect edges of roof images. Incorporating CNN into edge detection problem makes the whole system simple, fast, and reliable. Moreover, with no more extra training and without additional feature ex...
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), 2016
Macular retinal anomaly known as Drusen present in the eyes infected with Age Macular Degeneratio... more Macular retinal anomaly known as Drusen present in the eyes infected with Age Macular Degeneration (AMD) can be visualized with optical coherence tomography (OCT). This paper presents an algorithm to automatically segment retinal pigment epithelium (RPE) layer of an eye using spectral domain optical coherence tomography (SD-OCT) images for the detection of drusen. Segmentation framework is based on intensity level thresholding of high reflective pixels around retinal nerve fiber layer (RNFL). A dataset of 50 different B-scan is taken with having 25 AMD and 25 heathy images. Bottom layer of the retina known as RPE layer is extracted and analyzed by fitting a second order polynomial curve. The difference between both the curvess decide the class of the image. Results show an accurate detection of drusen with 96 % accuracy.
2021 IEEE 7th International Conference on Network Softwarization (NetSoft), 2021
Intent-Based Networking (IBN) is a model that enables proactive network control and automation to... more Intent-Based Networking (IBN) is a model that enables proactive network control and automation to satisfy high-level demands. It follows a closed-loop mechanism that abstracts the network complexity and dynamically allows updates to the network monitoring and intelligence. Hence, it eliminates the traditionally practiced error-prone manual network control. In contrast with the traditional reactive approach, IBN-based approach promotes the proactive and dynamic solution. To this end, IBN uses machine learning (ML) to predict the future and keeps a balance between the intended and actual state. Hence, this work considers an IBN-driven routing mechanism to ensure service provisioning with the desired quality of service (QoS). In contrast to the traditional static routing scheme, this work considers AI-driven dynamic and proactively updatable routing schemes to ensure QoS. This work demonstrates AI-driven service route control mechanism for ensuring quality of service (QoS) on top of Ko...
On-demand service is the main feature of the 5G network, and Network Function Virtualization (NFV... more On-demand service is the main feature of the 5G network, and Network Function Virtualization (NFV) provides it by virtualizing the existing 5G network infrastructure. NFV crafts various virtual networks on a shared physical network, but one of the core challenges in future 5G networks is to automate the modeling of Virtualized Network Functions (VNFs) and end-to-end Network Service (NS) orchestration with less human interaction. Traditionally, the descriptor of VNF and NS is created manually, which requires expert-level skills. This manual approach has a big threat of human error, which can be avoided by using the Intent-Based Networking (IBN) approach. The IBN approach eliminates the requirement of expertise for designing VNFs and NS by taking users’ intentions as an input. In this paper, the proposed system presents the Intent Management System for VNF modeling and end-to-end NS orchestration for multi-platforms. This system takes the high-level information related to a specific s...
The fifth-generation mobile network presents a wide range of services which have different requir... more The fifth-generation mobile network presents a wide range of services which have different requirements in terms of performance, bandwidth, reliability, and latency. The legacy networks are not capable to handle these diverse services with the same physical infrastructure. In this way, network virtualization presents a reliable solution named network slicing that supports service heterogeneity and provides differentiated resources to each service. Network slicing enables network operators to create multiple logical networks over a common physical infrastructure. In this research article, we have designed and implemented an intent-based network slicing system that can slice and manage the core network and radio access network (RAN) resources efficiently. It is an automated system, where users just need to provide higher-level network configurations in the form of intents/contracts for a network slice, and in return, our system deploys and configures the requested resources accordingl...
By the prediction of future location for a vehicle in Internet of Vehicles (IoV), data forwarding... more By the prediction of future location for a vehicle in Internet of Vehicles (IoV), data forwarding schemes can be further improved. Major parameters for vehicle position prediction includes traffic density, motion, road conditions, and vehicle current position. In this paper, therefore, our proposed system enforces the accurate prediction with the help of realtime traffic from the vehicles. In addition, the proposed Neural Network Model assists Edge Controller and centralized controller to compute and predict vehicle future position inside and outside of the vicinity, respectively. Last but not least, in order to get real-time data, and to maintain a quality of experience, the edge controller is explored with Software Defined Internet of Vehicles. In order to evaluate our framework, SUMO simulator with Open Street map is considered and the results prove the importance of vehicle position prediction for vehicular networks. Index Terms-Vehicle to Anything (V2X), position prediction, SDN, edge controllers, internet of vehicles, GIS, neural network I. INTRODUCTION Nowadays, vehicles on the road are increasing exponentially and it is expected that the count will go beyond 2.5 billion by 2050s [1]. With the exponential growth of traffic, the complexity of traffic management propagates in parallel. Intelligent Transportation System (ITS) is hot research among the autonomous industry with its varying road safety and entertainment applications [2]. The study of the connected car is one of the key research area and is being evolved under the umbrella of the Internet of Vehicles (IoV) [3], [4], a subfield of Internet of Things (IoT). The main focus of IoV is V2X communication, i.e. vehicle to everything (vehicle to infrastructure, vehicle, pedestrians, network gateways, and RSUs communication, etc. [5], [6]). V2X communication is considered as one of the vital technology explored by ITS for traffic assistance in a smart city. V2X communication consists of Dedicated Short Range Communications (DSRC) or cellular infrastructure, based on its requirement to their respective scenarios. However, a combination of both the technologies can also deliver promising results with high throughput and low latency for critical applications [7]. [8].
Container-based service orchestration is getting famous increasingly because of its ability to be... more Container-based service orchestration is getting famous increasingly because of its ability to be deployed quickly and it is cheaper as well as more reliable when compared to virtual machines. Leveraging the container characteristic, deployment of 5G modules as a group of containers on different nodes is an excellent solution to construct a 5g system. In a 5G system, network slicing plays a vital role to isolate the on-demand services and the SDN based overlay network consisting of containers provides the platform which manages to slice the network using intent-based networking. As the number of containers in a deployment increases on hosts across the overlay network with the passage of time in the 5G network, therefore it is necessary to manage them with the tool in a straight way with high-level abstraction. In this paper, we present the deployment of an overlay network which consists of Kubernetes nodes and Open vSwitch. In this paper, we also present the intent-based slicing system using Software Defined Network controller and an Intent-Based Networking (IBN) Manager among the containers across the Kubernetes pods in an overlay network. Index Terms-Containers, kubernetes, software-defined network, slicing, intent-based networking, overlay networking Wang-Cheol Song work at the Computer Engineering department, Jeju National University, South Korea. Member of Advanced Network Forum (correspondent), Korea Contents Association (correspondent Distinguished Service medal 2005), Korea Information Science Society (correspondent), Korean Institute Communications and Sciences (correspondent). He received B.S. degree in Food Engineering and Electronics
International Journal of Modern Education and Computer Science, 2013
In Project management, team's motivation is one of the most important factors in the success of a... more In Project management, team's motivation is one of the most important factors in the success of a project. Project Managersmanage the whole project by assuring that all the members are performing the duties they are assigned. Emotional Intelligence is the ability to identify the attitude of a team member towards a project. In developing countrieslack of emotional intelligence factors may cost people their jobs. In this paper conflict management, technical management, interest development and stress management problems are discussed with reference to developing countries and an efficient approach to resolve these issues is also proposed. Therefore project managers should raise their EI (emotional intelligence) and also help members to raise their EI. This paper explores the related work in EI, and then finds the useful Emotional Intelligence factors which are appropriate for the project manager. Then this paper also determinesa framework which is useful for project managers.
Requirement engineering is an essence of software development life cycle. The more time we spend ... more Requirement engineering is an essence of software development life cycle. The more time we spend on requirement engineering, higher the probability of success. Effective requirement engineering ensures and predicts successful software product. This paper presents the adaptation of requirement engineering practices in small and medium size companies of Pakistan. The study is conducted by questionnaires to show how much of requirement engineering models and practices are followed in Pakistan.
Uploads
Papers by Adeel Rafiq