Noman Islam - Academia.edu (original) (raw)
Papers by Noman Islam
2019 International Conference on Frontiers of Information Technology (FIT), 2019
In this paper, an agent-based cross-layer secure service discovery scheme has been presented. Ser... more In this paper, an agent-based cross-layer secure service discovery scheme has been presented. Service discovery in MANET is a critical task and it presents numerous security challenges. These threats can compromise the availability, privacy and integrity of service discovery process and infrastructure. This paper highlights various security challenges prevalent to service discovery in MANET. Then, in order to address these security challenges, the paper proposes a cross-layer, agent based secure service discovery scheme for MANET based on deep neural network. The software agents will monitor the intrusive activities in the network based on an Intrusion Detection System (IDS). The service discovery operation is performed based on periodic dissemination of service, routing and security information. The QoS provisioning is achieved by encapsulating QoS information in the periodic advertisements done by service providers. The proposed approach has been implemented in JIST/ SWANS simulat...
ArXiv, 2018
Cloud computing can be defined as the outsourcing / renting of resources over the network. It has... more Cloud computing can be defined as the outsourcing / renting of resources over the network. It has been regarded as an essential utility similar to electricity, water, telephone and sewerage utilities. Over the years, a number of providers have emerged that provide basic and advanced form of services for cloud computing. However, these providers employ their own nomenclature for marketing their specification and the range of services offered by them. This makes it very difficult for a common user to select a platform based on their requirements. This paper provides a comparison of different cloud service providers from an economic perspective. It performs the cost analysis of services provided by providers for different scenarios. Based on the analysis, conclusions have been drawn and directions for further research have been provided.
international journal of engineering trends and technology, 2020
Cloud computing enables aggregation of a pool of resources that are provided dynamically as a uti... more Cloud computing enables aggregation of a pool of resources that are provided dynamically as a utility to users over the internet. The users assume that infinite resources are available and pay only for the resources they consume. Different cloud computing providers have emerged during recent years, providing various services and features to endusers. Due to the diversity of the features provided by these providers, it becomes very difficult for an ordinary user to select a platform based on their requirements. This paper provides reflections on different cloud computing providers currently available in market. It analyzes the features provided by existing providers and summarizes the current options available to an ordinary user. Based on the comparative study, conclusions have been drawn and research avenues have been highlighted. Keywordscloud computing, high performance computing, cloud service provider, provider comparison
Optical Character Recognition (OCR) has been a topic of interest for many years. It is defined as... more Optical Character Recognition (OCR) has been a topic of interest for many years. It is defined as the process of digitizing a document image into its constituent characters. Despite decades of intense research, developing OCR with capabilities comparable to that of human still remains an open challenge. Due to this challenging nature, researchers from industry and academic circles have directed their attentions towards Optical Character Recognition. Over the last few years, the number of academic laboratories and companies involved in research on Character Recognition has increased dramatically. This research aims at summarizing the research so far done in the field of OCR. It provides an overview of different aspects of OCR and discusses corresponding proposals aimed at resolving issues of OCR.
2019 2nd International Conference on new Trends in Computing Sciences (ICTCS), 2019
This paper proposes an efficient and cost effective deep learning architecture to detect the diab... more This paper proposes an efficient and cost effective deep learning architecture to detect the diabetic retinopathy in real time. Diabetes is a leading root cause of eye disease in patients. It illuminates eye vessels, and releases blood form vessels. Early detection of diabetic retinopathy is useful to reduce the risk of blindness or any hazard. In this paper, after some preprocessing and data augmentation, Inception V3 is used as pre-trained model to extract the initial features set. Convolutional neural network has been used with attention layers. These additional CNN layers are added to extract the deep features to improve classification performance and accuracy. Initially, the model was proposed by Kevin Mader in Kaggle. The paper introduced additional layers in proposed model and improved the validation and testing accuracy significantly. More than 90% validation accuracy was achieved with the proposed Convolutional Neural Network model. Testing accuracy was improved up to 5%. T...
This paper presents an approach towards disaster management based on cognitive radio ad hoc netwo... more This paper presents an approach towards disaster management based on cognitive radio ad hoc network. Despite the growing interests on cognitive radio ad hoc networks, not much work has been reported on using them for disaster management. This paper discusses opportunities for disaster management based on cognitive radio ad hoc networks. In this direction, the paper presents a novel technique for disaster detection based on Artificial Neural Network (ANN). The ANN is trained using backward propagation algorithm. An ANN-based spectrum sensing scheme is also presented. Finally, a service discovery scheme is presented for coordination during the time of disaster. The simulation of proposed approach has been performed in NS-2 simulator. The proposed approach shows very low false negative alarm rate using the proposed disaster detection system. The spectrum switching time of spectrum sensing scheme is also analyzed along with an analysis of latency of proposed service discovery scheme
The latest evolving threats to modern cyber security is making difficult for public and private s... more The latest evolving threats to modern cyber security is making difficult for public and private sector organizations to protect their intellectual property and business information in digital form against theft, damage and misuse. Therefore, businesses need to become proactive and must have an adaptive approach in order to cater for this constant evolution of technology-related threats. In order to ensure successful cyber security strategy, Pakistan is facing two major problems. Firstly, there are no in-country formal trainings related to hacking. Therefore, only option is to have ethical hacker certification from abroad, which is expensive and beyond the approach of a mediocre citizen. Secondly, there is an acute crisis of job opportunities in the IT sector. In order to address these glaring issues; the Ministry of Defense, Interior Ministry and IT Ministry in liaison with Public and Private sector Universities of Pakistan has launched various programs for the development of legiti...
Context-Aware Computing involves sensing the context via sensors and other input channels, taking... more Context-Aware Computing involves sensing the context via sensors and other input channels, taking smart decisions, reflecting back the decisions and feedback tracking from the context. Agriculture is one of the key disciplines where context plays a vital role. Implementation of contextaware solutions in agriculture can be considered as an extension of Precision Agriculture. Very little work has been done in Context-Aware Agriculture. This involves transforming key agricultural concerns which follow traditional approaches to a context model governed via an I/O channel of sensors and actuators. The context model is a semantic model of the traditional practice. One novel approach to create context model is through building Ontology, use of wireless sensor and computing grids. In this paper, a context aware model of a typical watering process in agricultural fields have been developed and tested against the traditional practices. The results spanning over a large period of crop indicate...
2020 International Conference on Information Science and Communication Technology (ICISCT)
This paper proposes an image processing based approach to analyze the height and width of jump of... more This paper proposes an image processing based approach to analyze the height and width of jump of an athlete. Most of the existing approaches are based on using sensor’s technology for analysis of ski-jumps. This work differs from past approaches and is based on image processing techniques that employ various heuristics and Hog descriptor to find out the width and height of a jump. The proposed approach has been implemented in Open CV. It is based on first finding out the bounding box on human picture and then using KCF tracker for tracking object throughout the jumping process. The heuristic could be actual height of object in metric unit in case of jump and distance between two markers in case of speed. The video of the athlete will be recorded at fixed distance. For vertical and horizontal jump calculation, Euclidean or simple distance formula is used. The proposed approach is found to reliably calculate the jump’s height, length and speed of athlete.
Electronics
Cloud computing offers flexible, interactive, and observable access to shared resources on the In... more Cloud computing offers flexible, interactive, and observable access to shared resources on the Internet. It frees users from the requirements of managing computing on their hardware. It enables users to not only store their data and computing over the internet but also can access it whenever and wherever it is required. The frequent use of smart devices has helped cloud computing to realize the need for its rapid growth. As more users are adapting to the cloud environment, the focus has been placed on load balancing. Load balancing allocates tasks or resources to different devices. In cloud computing, and load balancing has played a major role in the efficient usage of resources for the highest performance. This requirement results in the development of algorithms that can optimally assign resources while managing load and improving quality of service (QoS). This paper provides a survey of load balancing algorithms inspired by swarm intelligence (SI). The algorithms considered in th...
EAI Endorsed Transactions on Pervasive Health and Technology
International Journal of Intelligent Engineering Informatics
Intelligent Automation & Soft Computing
Applied Sciences
In recent years, the consumption of social media content to keep up with global news and to verif... more In recent years, the consumption of social media content to keep up with global news and to verify its authenticity has become a considerable challenge. Social media enables us to easily access news anywhere, anytime, but it also gives rise to the spread of fake news, thereby delivering false information. This also has a negative impact on society. Therefore, it is necessary to determine whether or not news spreading over social media is real. This will allow for confusion among social media users to be avoided, and it is important in ensuring positive social development. This paper proposes a novel solution by detecting the authenticity of news through natural language processing techniques. Specifically, this paper proposes a novel scheme comprising three steps, namely, stance detection, author credibility verification, and machine learning-based classification, to verify the authenticity of news. In the last stage of the proposed pipeline, several machine learning techniques are ...
Research Anthology on Developing and Optimizing 5G Networks and the Impact on Society
Mobile communication witnesses a new generation after every 10 years. Following the same trend, t... more Mobile communication witnesses a new generation after every 10 years. Following the same trend, the roll out of next generation called 5G network is anticipated by 2020. In this chapter, a critical review of enabling technologies and research issues of 5G network is provided. The novelty of the chapter lies in providing a holistic view of 5G networks spanning discussions on technologies and issues across all the layers of protocol stack. Specifically, the chapter talks about the higher-level research issues of 5G network. The chapter is primarily structured as follows: It starts with a brief overview of various generations of mobile communication. Then, the problems with existing generation of mobile communication are presented, thus providing the motivation for a new generation of mobile network. A survey of different enabling technologies of 5G network is provided afterwards. After having brief discussions on key enablers, the chapter presents various research issues of 5G network...
Electronics
Bioacoustics plays an important role in the conservation of bird species. Bio-acoustic surveys ba... more Bioacoustics plays an important role in the conservation of bird species. Bio-acoustic surveys based on autonomous audio recording are both cost-effective and time-efficient. However, there are many bird species with different patterns of vocalization, and it is a challenging task to deal with them. Previous studies have revealed that many authors focus on the segmentation of bird audio without considering specific patterns of bird vocalization. Based on the existing literature, currently there is no work on the segmentation of monosyllabic and multisyllabic birds, separately. Therefore, this research addresses the aforementioned concern and also proposes a collection of audio features named ‘Perceptual, Descriptive, and Harmonic Features (PDHFs)’ that gives promising results in the classification of bird vocalization. Moreover, the classification results improved when monosyllabic and multisyllabic birds were classified separately. To analyze the performance of PDHFs, different cla...
Advances in Data Science and Adaptive Analysis
During the past few years, deep learning (DL) architectures are being employed in many potential ... more During the past few years, deep learning (DL) architectures are being employed in many potential areas such as object detection, face recognition, natural language processing, medical image analysis and other related applications. In these applications, DL has achieved remarkable results matching the performance of human experts. This paper presents a novel convolutional neural networks (CNN)-based approach for the detection of breast cancer in invasive ductal carcinoma tissue regions using whole slide images (WSI). It has been observed that breast cancer has been a leading cause of death among women. It also remains a striving task for pathologist to find the malignancy regions from WSI. In this research, we have implemented different CNN models which include VGG16, VGG19, Xception, Inception V3, MobileNetV2, ResNet50, and DenseNet. The experiments were performed on standard WSI slides data-set which include 163 patients of IDC. For performance evaluation, same data-set was divided into 113 and 49 images for training and testing, respectively. The testing was carried out separately over each model and the obtained results showed that our proposed CNN model achieved 83% accuracy which is better than the other models.
2019 International Conference on Frontiers of Information Technology (FIT), 2019
In this paper, an agent-based cross-layer secure service discovery scheme has been presented. Ser... more In this paper, an agent-based cross-layer secure service discovery scheme has been presented. Service discovery in MANET is a critical task and it presents numerous security challenges. These threats can compromise the availability, privacy and integrity of service discovery process and infrastructure. This paper highlights various security challenges prevalent to service discovery in MANET. Then, in order to address these security challenges, the paper proposes a cross-layer, agent based secure service discovery scheme for MANET based on deep neural network. The software agents will monitor the intrusive activities in the network based on an Intrusion Detection System (IDS). The service discovery operation is performed based on periodic dissemination of service, routing and security information. The QoS provisioning is achieved by encapsulating QoS information in the periodic advertisements done by service providers. The proposed approach has been implemented in JIST/ SWANS simulat...
ArXiv, 2018
Cloud computing can be defined as the outsourcing / renting of resources over the network. It has... more Cloud computing can be defined as the outsourcing / renting of resources over the network. It has been regarded as an essential utility similar to electricity, water, telephone and sewerage utilities. Over the years, a number of providers have emerged that provide basic and advanced form of services for cloud computing. However, these providers employ their own nomenclature for marketing their specification and the range of services offered by them. This makes it very difficult for a common user to select a platform based on their requirements. This paper provides a comparison of different cloud service providers from an economic perspective. It performs the cost analysis of services provided by providers for different scenarios. Based on the analysis, conclusions have been drawn and directions for further research have been provided.
international journal of engineering trends and technology, 2020
Cloud computing enables aggregation of a pool of resources that are provided dynamically as a uti... more Cloud computing enables aggregation of a pool of resources that are provided dynamically as a utility to users over the internet. The users assume that infinite resources are available and pay only for the resources they consume. Different cloud computing providers have emerged during recent years, providing various services and features to endusers. Due to the diversity of the features provided by these providers, it becomes very difficult for an ordinary user to select a platform based on their requirements. This paper provides reflections on different cloud computing providers currently available in market. It analyzes the features provided by existing providers and summarizes the current options available to an ordinary user. Based on the comparative study, conclusions have been drawn and research avenues have been highlighted. Keywordscloud computing, high performance computing, cloud service provider, provider comparison
Optical Character Recognition (OCR) has been a topic of interest for many years. It is defined as... more Optical Character Recognition (OCR) has been a topic of interest for many years. It is defined as the process of digitizing a document image into its constituent characters. Despite decades of intense research, developing OCR with capabilities comparable to that of human still remains an open challenge. Due to this challenging nature, researchers from industry and academic circles have directed their attentions towards Optical Character Recognition. Over the last few years, the number of academic laboratories and companies involved in research on Character Recognition has increased dramatically. This research aims at summarizing the research so far done in the field of OCR. It provides an overview of different aspects of OCR and discusses corresponding proposals aimed at resolving issues of OCR.
2019 2nd International Conference on new Trends in Computing Sciences (ICTCS), 2019
This paper proposes an efficient and cost effective deep learning architecture to detect the diab... more This paper proposes an efficient and cost effective deep learning architecture to detect the diabetic retinopathy in real time. Diabetes is a leading root cause of eye disease in patients. It illuminates eye vessels, and releases blood form vessels. Early detection of diabetic retinopathy is useful to reduce the risk of blindness or any hazard. In this paper, after some preprocessing and data augmentation, Inception V3 is used as pre-trained model to extract the initial features set. Convolutional neural network has been used with attention layers. These additional CNN layers are added to extract the deep features to improve classification performance and accuracy. Initially, the model was proposed by Kevin Mader in Kaggle. The paper introduced additional layers in proposed model and improved the validation and testing accuracy significantly. More than 90% validation accuracy was achieved with the proposed Convolutional Neural Network model. Testing accuracy was improved up to 5%. T...
This paper presents an approach towards disaster management based on cognitive radio ad hoc netwo... more This paper presents an approach towards disaster management based on cognitive radio ad hoc network. Despite the growing interests on cognitive radio ad hoc networks, not much work has been reported on using them for disaster management. This paper discusses opportunities for disaster management based on cognitive radio ad hoc networks. In this direction, the paper presents a novel technique for disaster detection based on Artificial Neural Network (ANN). The ANN is trained using backward propagation algorithm. An ANN-based spectrum sensing scheme is also presented. Finally, a service discovery scheme is presented for coordination during the time of disaster. The simulation of proposed approach has been performed in NS-2 simulator. The proposed approach shows very low false negative alarm rate using the proposed disaster detection system. The spectrum switching time of spectrum sensing scheme is also analyzed along with an analysis of latency of proposed service discovery scheme
The latest evolving threats to modern cyber security is making difficult for public and private s... more The latest evolving threats to modern cyber security is making difficult for public and private sector organizations to protect their intellectual property and business information in digital form against theft, damage and misuse. Therefore, businesses need to become proactive and must have an adaptive approach in order to cater for this constant evolution of technology-related threats. In order to ensure successful cyber security strategy, Pakistan is facing two major problems. Firstly, there are no in-country formal trainings related to hacking. Therefore, only option is to have ethical hacker certification from abroad, which is expensive and beyond the approach of a mediocre citizen. Secondly, there is an acute crisis of job opportunities in the IT sector. In order to address these glaring issues; the Ministry of Defense, Interior Ministry and IT Ministry in liaison with Public and Private sector Universities of Pakistan has launched various programs for the development of legiti...
Context-Aware Computing involves sensing the context via sensors and other input channels, taking... more Context-Aware Computing involves sensing the context via sensors and other input channels, taking smart decisions, reflecting back the decisions and feedback tracking from the context. Agriculture is one of the key disciplines where context plays a vital role. Implementation of contextaware solutions in agriculture can be considered as an extension of Precision Agriculture. Very little work has been done in Context-Aware Agriculture. This involves transforming key agricultural concerns which follow traditional approaches to a context model governed via an I/O channel of sensors and actuators. The context model is a semantic model of the traditional practice. One novel approach to create context model is through building Ontology, use of wireless sensor and computing grids. In this paper, a context aware model of a typical watering process in agricultural fields have been developed and tested against the traditional practices. The results spanning over a large period of crop indicate...
2020 International Conference on Information Science and Communication Technology (ICISCT)
This paper proposes an image processing based approach to analyze the height and width of jump of... more This paper proposes an image processing based approach to analyze the height and width of jump of an athlete. Most of the existing approaches are based on using sensor’s technology for analysis of ski-jumps. This work differs from past approaches and is based on image processing techniques that employ various heuristics and Hog descriptor to find out the width and height of a jump. The proposed approach has been implemented in Open CV. It is based on first finding out the bounding box on human picture and then using KCF tracker for tracking object throughout the jumping process. The heuristic could be actual height of object in metric unit in case of jump and distance between two markers in case of speed. The video of the athlete will be recorded at fixed distance. For vertical and horizontal jump calculation, Euclidean or simple distance formula is used. The proposed approach is found to reliably calculate the jump’s height, length and speed of athlete.
Electronics
Cloud computing offers flexible, interactive, and observable access to shared resources on the In... more Cloud computing offers flexible, interactive, and observable access to shared resources on the Internet. It frees users from the requirements of managing computing on their hardware. It enables users to not only store their data and computing over the internet but also can access it whenever and wherever it is required. The frequent use of smart devices has helped cloud computing to realize the need for its rapid growth. As more users are adapting to the cloud environment, the focus has been placed on load balancing. Load balancing allocates tasks or resources to different devices. In cloud computing, and load balancing has played a major role in the efficient usage of resources for the highest performance. This requirement results in the development of algorithms that can optimally assign resources while managing load and improving quality of service (QoS). This paper provides a survey of load balancing algorithms inspired by swarm intelligence (SI). The algorithms considered in th...
EAI Endorsed Transactions on Pervasive Health and Technology
International Journal of Intelligent Engineering Informatics
Intelligent Automation & Soft Computing
Applied Sciences
In recent years, the consumption of social media content to keep up with global news and to verif... more In recent years, the consumption of social media content to keep up with global news and to verify its authenticity has become a considerable challenge. Social media enables us to easily access news anywhere, anytime, but it also gives rise to the spread of fake news, thereby delivering false information. This also has a negative impact on society. Therefore, it is necessary to determine whether or not news spreading over social media is real. This will allow for confusion among social media users to be avoided, and it is important in ensuring positive social development. This paper proposes a novel solution by detecting the authenticity of news through natural language processing techniques. Specifically, this paper proposes a novel scheme comprising three steps, namely, stance detection, author credibility verification, and machine learning-based classification, to verify the authenticity of news. In the last stage of the proposed pipeline, several machine learning techniques are ...
Research Anthology on Developing and Optimizing 5G Networks and the Impact on Society
Mobile communication witnesses a new generation after every 10 years. Following the same trend, t... more Mobile communication witnesses a new generation after every 10 years. Following the same trend, the roll out of next generation called 5G network is anticipated by 2020. In this chapter, a critical review of enabling technologies and research issues of 5G network is provided. The novelty of the chapter lies in providing a holistic view of 5G networks spanning discussions on technologies and issues across all the layers of protocol stack. Specifically, the chapter talks about the higher-level research issues of 5G network. The chapter is primarily structured as follows: It starts with a brief overview of various generations of mobile communication. Then, the problems with existing generation of mobile communication are presented, thus providing the motivation for a new generation of mobile network. A survey of different enabling technologies of 5G network is provided afterwards. After having brief discussions on key enablers, the chapter presents various research issues of 5G network...
Electronics
Bioacoustics plays an important role in the conservation of bird species. Bio-acoustic surveys ba... more Bioacoustics plays an important role in the conservation of bird species. Bio-acoustic surveys based on autonomous audio recording are both cost-effective and time-efficient. However, there are many bird species with different patterns of vocalization, and it is a challenging task to deal with them. Previous studies have revealed that many authors focus on the segmentation of bird audio without considering specific patterns of bird vocalization. Based on the existing literature, currently there is no work on the segmentation of monosyllabic and multisyllabic birds, separately. Therefore, this research addresses the aforementioned concern and also proposes a collection of audio features named ‘Perceptual, Descriptive, and Harmonic Features (PDHFs)’ that gives promising results in the classification of bird vocalization. Moreover, the classification results improved when monosyllabic and multisyllabic birds were classified separately. To analyze the performance of PDHFs, different cla...
Advances in Data Science and Adaptive Analysis
During the past few years, deep learning (DL) architectures are being employed in many potential ... more During the past few years, deep learning (DL) architectures are being employed in many potential areas such as object detection, face recognition, natural language processing, medical image analysis and other related applications. In these applications, DL has achieved remarkable results matching the performance of human experts. This paper presents a novel convolutional neural networks (CNN)-based approach for the detection of breast cancer in invasive ductal carcinoma tissue regions using whole slide images (WSI). It has been observed that breast cancer has been a leading cause of death among women. It also remains a striving task for pathologist to find the malignancy regions from WSI. In this research, we have implemented different CNN models which include VGG16, VGG19, Xception, Inception V3, MobileNetV2, ResNet50, and DenseNet. The experiments were performed on standard WSI slides data-set which include 163 patients of IDC. For performance evaluation, same data-set was divided into 113 and 49 images for training and testing, respectively. The testing was carried out separately over each model and the obtained results showed that our proposed CNN model achieved 83% accuracy which is better than the other models.