MULTI-ASPECT URDU HANDWRITING DATA COLLECTION, 2023
Urdu script is categorized as one of the cursive and bidirectional script derived from Arabic and... more Urdu script is categorized as one of the cursive and bidirectional script derived from Arabic and Persian script; this is the reason Urdu script shares almost similar challenges and issues but with higher complexity. There is a lack of freely available public datasets for the research in the field of Urdu handwriting recognition. In this paper, we propose a multi-aspect Urdu handwriting data collection by inviting a number of native Urdu speakers from different social groups. To make the dataset more comprehensive, both the isolated characters and the ligatures are included in the dataset. Furthermore, the persons having physical disability are also invited for data collection to make the corpus more comprehensive. We also give a review of existing data collections for Urdu handwriting recognition and give a comparison of the proposed data collection with existing ones.
Euler path is one of the most interesting and widely discussed topics in graph theory. An Euler p... more Euler path is one of the most interesting and widely discussed topics in graph theory. An Euler path (or Euler trail) is a path that visits every edge of a graph exactly once. Similarly, an Euler circuit (or Euler cycle) is an Euler trail that starts and ends on the same node of a graph. A graph having Euler path is called Euler graph. While tracing Euler graph, one may halt at arbitrary nodes while some of its edges left unvisited. In this paper, we have proposed some precautionary steps that should be considered in exploring a deadlock-free Euler path, i.e., without being halted at any node. Simulation results show that our proposed approach improves the process of exploring the Euler path in an undirected connected graph without interruption. Furthermore, our proposed algorithm is complete for all types of undirected Eulerian graphs. The paper concludes with the proofs of the correctness of proposed algorithm and its computation complexity.
Agile methodologies are taking over the traditional software development methodologies with the p... more Agile methodologies are taking over the traditional software development methodologies with the passage of time. These methodologies involve more benefits than traditional software development methodologies and very fewer drawbacks. Due to these benefits, the software development teams are more involved in Agile methodologies. There are a number of Agile methodologies which are famous in software development community. Each of them has its own benefits and drawbacks. Proposing one suitable Agile methodology for a project may benefit the project in one direction but may also cause the project to suffer in some other direction. Due to this fact, the idea of hybrid Agile methodologies evolved. DXPRUM is also one of those hybrid methodologies and is a combination of DSDM, XP, and Scrum. This paper presents a comparative study of DXPRUM and DSDM by applying them to some real time projects and thus comparing their results.
In this research paper, we evaluate Voice-over Internet Protocol (VoIP) technology, implement and... more In this research paper, we evaluate Voice-over Internet Protocol (VoIP) technology, implement and integrate VoIP with IP Private Branch Exchange (IP PBX), track the behavior of data and voice quality using different voice codec and provide the appropriate solutions to improve the quality and reduce the cost of the customer’s calls. The main issue is to identify the problematic areas when network is under attack. We introduce VoIP BOX which optimize the bandwidth, improve the reliability, scalability and security of customer’s calls. We also examine the attacks on VoIP PBX network and provide the appropriate solutions how to stop or minimize the internal and external attacks launched by Attacker. The introduced VoIP BOX which is integrated with VoIP PBX, achieves quality of service on low bandwidth, almost zero jitter and high security.
The main objective of this study is to find out the importance of machine vision approach for the... more The main objective of this study is to find out the importance of machine vision approach for the classification of five types of land cover data such as bare land, desert rangeland, green pasture, fertile cultivated land, and Sutlej river land. A novel spectra-statistical framework is designed to classify the subjective land cover data types accurately. Multispectral data of these land covers were acquired by using a handheld device named multispectral radiometer in the form of five spectral bands (blue, green, red, near infrared, and shortwave infrared) while texture data were acquired with a digital camera by the transformation of acquired images into 229 texture features for each image. The most discriminant 30 features of each image were obtained by integrating the three statistical features selection techniques such as Fisher, Probability of Error plus Average Correlation, and Mutual Information (F + PA + MI). Selected texture data clustering was verified by nonlinear discriminant analysis while linear discriminant analysis approach was applied for multispectral data. For classification, the texture and multispectral data were deployed to artificial neural network (ANN: n-class). By implementing a cross validation method (80-20), we received an accuracy of 91.332% for texture data and 96.40% for multispectral data, respectively.
This research presents a classification based novel artificial intelligence approach of Mango Lea... more This research presents a classification based novel artificial intelligence approach of Mango Leaves recognition. The design and implementation of an artificial neural network system that extracts specific shape and morphological features from mango plant leaves of three kinds is presented in this research. Modules of significant mango leaf image features are identified using a novel feature selection technique. This technique reduces the dimensionality of the feature space leading to a simplified classification and identification scheme appropriate for real time classification systems for better results. In making the system complete, a full account is given of the necessary image processing methods that are applied to the binary images of mango plant leaves to ensure identification. These methods include the extraction of shapes from binary images. The proposed method inherits size and orientation invariance with respect to the image datasets and it can operate successfully even with leaves samples that are deformed due to dropout or due a number of holes drilled in them. A considerably very high classification ratio of 96% to 98% was achieved, even for the identification of deformed leaves.
In software, faults can occur and may disturb the normal behavior or working on a system. Softwar... more In software, faults can occur and may disturb the normal behavior or working on a system. Software fault tolerance techniques must implement to remove these faults. Fault tolerance defined as how the system fights when faults occur. A system cannot be truly fault tolerant until software fault tolerance techniques are applied to it. In early researches it is estimated that almost 60-90% of system failures are attributed to software failures. These failures can be controlled by applying software fault tolerance techniques. In this study, a comparative study of different software fault tolerance techniques (like Swift, Trump, Mask and N-version programming) is carried out and current research challenges in these techniques is also discussed.
Morphological filters erosion and dilation plays an important role for highlighting the buildings... more Morphological filters erosion and dilation plays an important role for highlighting the buildings and roads areas in aerial images. These filters give better results for classification of particular building and road areas in Images which are our region of interest. Image processing is a dynamic field and in recent years it is applied in many areas like medical sciences, remote sensing, military defense system, physical sciences and aerospace for useful purposes. This research paper focuses the study of highly resoluted aerial image of populated area. By applying different image processing techniques on aerial images like red band extraction, edge detection, enhanced gray level, texture features, red band replacement, binary threshold and finding the objects and classes of the image. By considering a particular range of buildings and roads objects then reconstruct the subjected images. At the end these buildings and road areas are highlighted by applying morphological filter erosion and dilation. We have taken the aerial image of Lahore Canal bank Road by Google earth and implemented all the above discussed techniques on it. The implemented techniques highlighted the building and road areas with red color.
During previous years, some movements have been widely discussed in the software development comm... more During previous years, some movements have been widely discussed in the software development community: Agile and open source development. Both have faced some of the same criticism, and both claim some of the same benefits. This study discusses the question, whether open source software development is in accordance with agile software development principles and therefore well within the planning spectrum? A comparative study is discussed about small scale open source projects by implementing Scrum and Feature Driven Development (FDD).Scrum is useful when requirements were not only incomplete at the start, but also could change rapidly during development phase. Scrum is concerned with functionality, but when we see that there is a functionality collapse; an alternative way is adopted, which is FDD which work upon domain base. In this study we compare that for Open Source Software (OSS), which methodology is good (SCRUM or FDD) for requirement gathering of OSS projects. We will also compare and conclude that which of the two methodologies (SCRUM or FDD) is good for requirements gathering of OSS projects.
This research aims to find the influence of rigorous requirement engineering activities in helpin... more This research aims to find the influence of rigorous requirement engineering activities in helping the developers to change over from the traditional ‘heavyweight’ methodologies to the Agile methodology. Four software projects were chosen as case studies from different software houses and research was conducted during their project life cycle. A decision support system assisted the development team to analyze the requirements gathered in requirement elicitation phase and recommended suitable development methodology for fulfilling them. Scrum methodology was recommended for all four case studies. In the next stage the progress of these projects were evaluated to determine the effectiveness of this combination of Scrum and Requirement engineering. A general improvement in the performance of the development process was reported after applying Scrum methodology under the umbrella of customer oriented requirement engineering.
Agile methods are being used as a new way of developing software. They are basically used to fast... more Agile methods are being used as a new way of developing software. They are basically used to fasten software development cycle by keeping an eye on its quality. Using Agile methods in any project along with quality assurance perspective is a crucial task. Many software developing organizations are using Agile methods now a days in their projects to reduce cost involved in a project. Agile methods are best suited for small projects as they require less resources and are able to generate output in less time. However, many organizations are also using Agile methods for medium and large scale projects. These projects also use large teams. Moreover, there may be teams having members taking part in these projects at geographically distributed locations. Assuring quality of these projects using Agile method is a challenging task. In Agile, testing is also carried out during all iterations along with software development. So the system has to be up and running every time for testing purpose. It means testing is only easy when organizations are working on small projects. As the size of the projects increases, the quality assurance of these projects also becomes a difficult task. The projects become complex as they require more resources and time, so there is always a burden on quality assurance team to deliver. The project may go for days and weeks without a functional build and thus testing cannot be done on regular basis. Secondly as the size of the project gets larger by adding more and more features in it, the number of tests is also increased to assure that the system is still performing what it is supposed to perform. The assurance of the quality of such projects is always a difficult task for any quality assurance team. Many Agile methods are being used by software developing organizations to build high quality software which involve less cost and time. Each Agile method has its own strengths and weaknesses. This research work is based on purposing a new hybrid Agile methodology DXPRUM. The DXPRUM is a combination of three of the agile models named as Dynamic Systems Development Method, Extreme Programming and Scrum (D comes from DSDM, XP from Extreme Programing, RUM from Scrum). The objective of the research is to purpose a new Agile methodology DXPRUM which combines the strengths of all the three Agile methods by removing their weaknesses. The main strength of DXPRUM will be the in time delivery of the project to customer with reduced cost. This research will consider a medium scale project with the implementation of a new Agile methodology DXPRUM under the perspective of quality assurance. The results of this research will also be compared with results of all three methods individually to validate the research. The metrics used for the evaluation will be total time in weeks, total number of modules build, total predicted hours, total line of code (LOC) and pre and post release defects etc.
Operating systems serve as executing platforms and
resource manager and supervisors for the appli... more Operating systems serve as executing platforms and resource manager and supervisors for the applications in running phase. With the development of more complex computer systems and applications, the required operating systems become complex too. But the proper management of such complex operating systems by human beings has shown to be impractical. Nowadays, self-managing concepts provide the basis for developing appropriate mechanisms to handle complex systems with minimum human interventions. Although the implications of deploying self-managing and autonomic attributes and concepts at the application levels have been studied, their deployment at system software level such as in operating systems have not been fully studied. Self-managed applications may not enjoy the whole benefit of self-management if the platform on which they run, specially its operating system, is not selfmanaged. Given this requirement, this paper highlights the most frequently occurred faults and anomalies of operating systems, and proposes a tiered operating system architecture and model, and a corresponding self-healing mechanism using machine learning techniques to show how self-managing can be realized at operating system level. Based on the principles of autonomic computing and self-adapting system research, we identify selfhealing systems’ fundamental principles. The main objective has been to design the operating system resilient to operating system faults without restarting the operating system and less human interaction.
MULTI-ASPECT URDU HANDWRITING DATA COLLECTION, 2023
Urdu script is categorized as one of the cursive and bidirectional script derived from Arabic and... more Urdu script is categorized as one of the cursive and bidirectional script derived from Arabic and Persian script; this is the reason Urdu script shares almost similar challenges and issues but with higher complexity. There is a lack of freely available public datasets for the research in the field of Urdu handwriting recognition. In this paper, we propose a multi-aspect Urdu handwriting data collection by inviting a number of native Urdu speakers from different social groups. To make the dataset more comprehensive, both the isolated characters and the ligatures are included in the dataset. Furthermore, the persons having physical disability are also invited for data collection to make the corpus more comprehensive. We also give a review of existing data collections for Urdu handwriting recognition and give a comparison of the proposed data collection with existing ones.
Euler path is one of the most interesting and widely discussed topics in graph theory. An Euler p... more Euler path is one of the most interesting and widely discussed topics in graph theory. An Euler path (or Euler trail) is a path that visits every edge of a graph exactly once. Similarly, an Euler circuit (or Euler cycle) is an Euler trail that starts and ends on the same node of a graph. A graph having Euler path is called Euler graph. While tracing Euler graph, one may halt at arbitrary nodes while some of its edges left unvisited. In this paper, we have proposed some precautionary steps that should be considered in exploring a deadlock-free Euler path, i.e., without being halted at any node. Simulation results show that our proposed approach improves the process of exploring the Euler path in an undirected connected graph without interruption. Furthermore, our proposed algorithm is complete for all types of undirected Eulerian graphs. The paper concludes with the proofs of the correctness of proposed algorithm and its computation complexity.
Agile methodologies are taking over the traditional software development methodologies with the p... more Agile methodologies are taking over the traditional software development methodologies with the passage of time. These methodologies involve more benefits than traditional software development methodologies and very fewer drawbacks. Due to these benefits, the software development teams are more involved in Agile methodologies. There are a number of Agile methodologies which are famous in software development community. Each of them has its own benefits and drawbacks. Proposing one suitable Agile methodology for a project may benefit the project in one direction but may also cause the project to suffer in some other direction. Due to this fact, the idea of hybrid Agile methodologies evolved. DXPRUM is also one of those hybrid methodologies and is a combination of DSDM, XP, and Scrum. This paper presents a comparative study of DXPRUM and DSDM by applying them to some real time projects and thus comparing their results.
In this research paper, we evaluate Voice-over Internet Protocol (VoIP) technology, implement and... more In this research paper, we evaluate Voice-over Internet Protocol (VoIP) technology, implement and integrate VoIP with IP Private Branch Exchange (IP PBX), track the behavior of data and voice quality using different voice codec and provide the appropriate solutions to improve the quality and reduce the cost of the customer’s calls. The main issue is to identify the problematic areas when network is under attack. We introduce VoIP BOX which optimize the bandwidth, improve the reliability, scalability and security of customer’s calls. We also examine the attacks on VoIP PBX network and provide the appropriate solutions how to stop or minimize the internal and external attacks launched by Attacker. The introduced VoIP BOX which is integrated with VoIP PBX, achieves quality of service on low bandwidth, almost zero jitter and high security.
The main objective of this study is to find out the importance of machine vision approach for the... more The main objective of this study is to find out the importance of machine vision approach for the classification of five types of land cover data such as bare land, desert rangeland, green pasture, fertile cultivated land, and Sutlej river land. A novel spectra-statistical framework is designed to classify the subjective land cover data types accurately. Multispectral data of these land covers were acquired by using a handheld device named multispectral radiometer in the form of five spectral bands (blue, green, red, near infrared, and shortwave infrared) while texture data were acquired with a digital camera by the transformation of acquired images into 229 texture features for each image. The most discriminant 30 features of each image were obtained by integrating the three statistical features selection techniques such as Fisher, Probability of Error plus Average Correlation, and Mutual Information (F + PA + MI). Selected texture data clustering was verified by nonlinear discriminant analysis while linear discriminant analysis approach was applied for multispectral data. For classification, the texture and multispectral data were deployed to artificial neural network (ANN: n-class). By implementing a cross validation method (80-20), we received an accuracy of 91.332% for texture data and 96.40% for multispectral data, respectively.
This research presents a classification based novel artificial intelligence approach of Mango Lea... more This research presents a classification based novel artificial intelligence approach of Mango Leaves recognition. The design and implementation of an artificial neural network system that extracts specific shape and morphological features from mango plant leaves of three kinds is presented in this research. Modules of significant mango leaf image features are identified using a novel feature selection technique. This technique reduces the dimensionality of the feature space leading to a simplified classification and identification scheme appropriate for real time classification systems for better results. In making the system complete, a full account is given of the necessary image processing methods that are applied to the binary images of mango plant leaves to ensure identification. These methods include the extraction of shapes from binary images. The proposed method inherits size and orientation invariance with respect to the image datasets and it can operate successfully even with leaves samples that are deformed due to dropout or due a number of holes drilled in them. A considerably very high classification ratio of 96% to 98% was achieved, even for the identification of deformed leaves.
In software, faults can occur and may disturb the normal behavior or working on a system. Softwar... more In software, faults can occur and may disturb the normal behavior or working on a system. Software fault tolerance techniques must implement to remove these faults. Fault tolerance defined as how the system fights when faults occur. A system cannot be truly fault tolerant until software fault tolerance techniques are applied to it. In early researches it is estimated that almost 60-90% of system failures are attributed to software failures. These failures can be controlled by applying software fault tolerance techniques. In this study, a comparative study of different software fault tolerance techniques (like Swift, Trump, Mask and N-version programming) is carried out and current research challenges in these techniques is also discussed.
Morphological filters erosion and dilation plays an important role for highlighting the buildings... more Morphological filters erosion and dilation plays an important role for highlighting the buildings and roads areas in aerial images. These filters give better results for classification of particular building and road areas in Images which are our region of interest. Image processing is a dynamic field and in recent years it is applied in many areas like medical sciences, remote sensing, military defense system, physical sciences and aerospace for useful purposes. This research paper focuses the study of highly resoluted aerial image of populated area. By applying different image processing techniques on aerial images like red band extraction, edge detection, enhanced gray level, texture features, red band replacement, binary threshold and finding the objects and classes of the image. By considering a particular range of buildings and roads objects then reconstruct the subjected images. At the end these buildings and road areas are highlighted by applying morphological filter erosion and dilation. We have taken the aerial image of Lahore Canal bank Road by Google earth and implemented all the above discussed techniques on it. The implemented techniques highlighted the building and road areas with red color.
During previous years, some movements have been widely discussed in the software development comm... more During previous years, some movements have been widely discussed in the software development community: Agile and open source development. Both have faced some of the same criticism, and both claim some of the same benefits. This study discusses the question, whether open source software development is in accordance with agile software development principles and therefore well within the planning spectrum? A comparative study is discussed about small scale open source projects by implementing Scrum and Feature Driven Development (FDD).Scrum is useful when requirements were not only incomplete at the start, but also could change rapidly during development phase. Scrum is concerned with functionality, but when we see that there is a functionality collapse; an alternative way is adopted, which is FDD which work upon domain base. In this study we compare that for Open Source Software (OSS), which methodology is good (SCRUM or FDD) for requirement gathering of OSS projects. We will also compare and conclude that which of the two methodologies (SCRUM or FDD) is good for requirements gathering of OSS projects.
This research aims to find the influence of rigorous requirement engineering activities in helpin... more This research aims to find the influence of rigorous requirement engineering activities in helping the developers to change over from the traditional ‘heavyweight’ methodologies to the Agile methodology. Four software projects were chosen as case studies from different software houses and research was conducted during their project life cycle. A decision support system assisted the development team to analyze the requirements gathered in requirement elicitation phase and recommended suitable development methodology for fulfilling them. Scrum methodology was recommended for all four case studies. In the next stage the progress of these projects were evaluated to determine the effectiveness of this combination of Scrum and Requirement engineering. A general improvement in the performance of the development process was reported after applying Scrum methodology under the umbrella of customer oriented requirement engineering.
Agile methods are being used as a new way of developing software. They are basically used to fast... more Agile methods are being used as a new way of developing software. They are basically used to fasten software development cycle by keeping an eye on its quality. Using Agile methods in any project along with quality assurance perspective is a crucial task. Many software developing organizations are using Agile methods now a days in their projects to reduce cost involved in a project. Agile methods are best suited for small projects as they require less resources and are able to generate output in less time. However, many organizations are also using Agile methods for medium and large scale projects. These projects also use large teams. Moreover, there may be teams having members taking part in these projects at geographically distributed locations. Assuring quality of these projects using Agile method is a challenging task. In Agile, testing is also carried out during all iterations along with software development. So the system has to be up and running every time for testing purpose. It means testing is only easy when organizations are working on small projects. As the size of the projects increases, the quality assurance of these projects also becomes a difficult task. The projects become complex as they require more resources and time, so there is always a burden on quality assurance team to deliver. The project may go for days and weeks without a functional build and thus testing cannot be done on regular basis. Secondly as the size of the project gets larger by adding more and more features in it, the number of tests is also increased to assure that the system is still performing what it is supposed to perform. The assurance of the quality of such projects is always a difficult task for any quality assurance team. Many Agile methods are being used by software developing organizations to build high quality software which involve less cost and time. Each Agile method has its own strengths and weaknesses. This research work is based on purposing a new hybrid Agile methodology DXPRUM. The DXPRUM is a combination of three of the agile models named as Dynamic Systems Development Method, Extreme Programming and Scrum (D comes from DSDM, XP from Extreme Programing, RUM from Scrum). The objective of the research is to purpose a new Agile methodology DXPRUM which combines the strengths of all the three Agile methods by removing their weaknesses. The main strength of DXPRUM will be the in time delivery of the project to customer with reduced cost. This research will consider a medium scale project with the implementation of a new Agile methodology DXPRUM under the perspective of quality assurance. The results of this research will also be compared with results of all three methods individually to validate the research. The metrics used for the evaluation will be total time in weeks, total number of modules build, total predicted hours, total line of code (LOC) and pre and post release defects etc.
Operating systems serve as executing platforms and
resource manager and supervisors for the appli... more Operating systems serve as executing platforms and resource manager and supervisors for the applications in running phase. With the development of more complex computer systems and applications, the required operating systems become complex too. But the proper management of such complex operating systems by human beings has shown to be impractical. Nowadays, self-managing concepts provide the basis for developing appropriate mechanisms to handle complex systems with minimum human interventions. Although the implications of deploying self-managing and autonomic attributes and concepts at the application levels have been studied, their deployment at system software level such as in operating systems have not been fully studied. Self-managed applications may not enjoy the whole benefit of self-management if the platform on which they run, specially its operating system, is not selfmanaged. Given this requirement, this paper highlights the most frequently occurred faults and anomalies of operating systems, and proposes a tiered operating system architecture and model, and a corresponding self-healing mechanism using machine learning techniques to show how self-managing can be realized at operating system level. Based on the principles of autonomic computing and self-adapting system research, we identify selfhealing systems’ fundamental principles. The main objective has been to design the operating system resilient to operating system faults without restarting the operating system and less human interaction.
Uploads
The proposed method inherits size and orientation invariance with respect to the image datasets and it can operate successfully even with leaves samples that are deformed due to dropout or due a number of holes drilled in them. A considerably very high classification ratio of 96% to 98% was achieved, even for the identification of deformed leaves.
resource manager and supervisors for the applications in
running phase. With the development of more complex computer
systems and applications, the required operating systems become
complex too. But the proper management of such complex
operating systems by human beings has shown to be impractical.
Nowadays, self-managing concepts provide the basis for
developing appropriate mechanisms to handle complex systems
with minimum human interventions. Although the implications
of deploying self-managing and autonomic attributes and
concepts at the application levels have been studied, their
deployment at system software level such as in operating systems
have not been fully studied. Self-managed applications may not
enjoy the whole benefit of self-management if the platform on
which they run, specially its operating system, is not selfmanaged.
Given this requirement, this paper highlights the most
frequently occurred faults and anomalies of operating systems,
and proposes a tiered operating system architecture and model,
and a corresponding self-healing mechanism using machine
learning techniques to show how self-managing can be realized
at operating system level. Based on the principles of autonomic
computing and self-adapting system research, we identify selfhealing
systems’ fundamental principles. The main objective has
been to design the operating system resilient to operating system
faults without restarting the operating system and less human
interaction.
The proposed method inherits size and orientation invariance with respect to the image datasets and it can operate successfully even with leaves samples that are deformed due to dropout or due a number of holes drilled in them. A considerably very high classification ratio of 96% to 98% was achieved, even for the identification of deformed leaves.
resource manager and supervisors for the applications in
running phase. With the development of more complex computer
systems and applications, the required operating systems become
complex too. But the proper management of such complex
operating systems by human beings has shown to be impractical.
Nowadays, self-managing concepts provide the basis for
developing appropriate mechanisms to handle complex systems
with minimum human interventions. Although the implications
of deploying self-managing and autonomic attributes and
concepts at the application levels have been studied, their
deployment at system software level such as in operating systems
have not been fully studied. Self-managed applications may not
enjoy the whole benefit of self-management if the platform on
which they run, specially its operating system, is not selfmanaged.
Given this requirement, this paper highlights the most
frequently occurred faults and anomalies of operating systems,
and proposes a tiered operating system architecture and model,
and a corresponding self-healing mechanism using machine
learning techniques to show how self-managing can be realized
at operating system level. Based on the principles of autonomic
computing and self-adapting system research, we identify selfhealing
systems’ fundamental principles. The main objective has
been to design the operating system resilient to operating system
faults without restarting the operating system and less human
interaction.