Dr. Tayyaba Anees - Academia.edu (original) (raw)
Papers by Dr. Tayyaba Anees
Complex & Intelligent Systems
Deep learning for image retrieval has been used in this era, but image retrieval with the highest... more Deep learning for image retrieval has been used in this era, but image retrieval with the highest accuracy is the biggest challenge, which still lacks auto-correlation for feature extraction and description. In this paper, a novel deep learning technique for achieving highly accurate results for image retrieval is proposed, which implements a convolutional neural network with auto-correlation, gradient computation, scaling, filter, and localization coupled with state-of-the-art content-based image retrieval methods. For this purpose, novel image features are fused with signatures produced by the VGG-16. In the initial step, images from rectangular neighboring key points are auto-correlated. The image smoothing is achieved by computing intensities according to the local gradient. The result of Gaussian approximation with the lowest scale and suppression is adjusted by the by-box filter with the standard deviation adjusted to the lowest scale. The parameterized images are smoothed at ...
Knowledge and Information Systems
Multimedia Tools and Applications
Coronavirus (COVID-19) has adversely harmed the healthcare system and economy throughout the worl... more Coronavirus (COVID-19) has adversely harmed the healthcare system and economy throughout the world. COVID-19 has similar symptoms as other chest disorders such as lung cancer (LC), pneumothorax, tuberculosis (TB), and pneumonia, which might mislead the clinical professionals in detecting a new variant of flu called coronavirus. This motivates us to design a model to classify multi-chest infections. A chest x-ray is the most ubiquitous disease diagnosis process in medical practice. As a result, chest x-ray examinations are the primary diagnostic tool for all of these chest infections. For the sake of saving human lives, paramedics and researchers are working tirelessly to establish a precise and reliable method for diagnosing the disease COVID-19 at an early stage. However, COVID-19's medical diagnosis is exceedingly idiosyncratic and varied. A multi-classification method based on the deep learning (DL) model is developed and tested in this work to automatically classify the COVID-19, LC, pneumothorax, TB, and pneumonia from chest x-ray images. COVID-19 and other chest tract disorders are diagnosed using a convolutional neural network (CNN) model called CDC Net that incorporates residual network thoughts and dilated convolution. For this study, we used this model in conjunction with publically available benchmark data to identify these diseases. For the first time, a single deep learning model has been used to diagnose five different chest ailments. In terms of classification accuracy, recall, precision, and f1-score, we compared the proposed model to three CNN-based pre-trained models, such as Vgg-19, ResNet-50, and inception v3. An AUC of 0.9953 was attained by the CDC Net when Multimedia Tools and Applications
2021 International Conference on Innovative Computing (ICIC), 2021
Automatic land cover classification through satellite imagery is an important remote sensing prob... more Automatic land cover classification through satellite imagery is an important remote sensing problem. Varying satellite-sensor’s characteristics reflect their own differences in the images and a sensor independent solution to the problem becomes difficult in general. Along with the sensor specific variations, the time at which the image is captured is yet another parameter. We propose an efficient method for village segmentation. The satellite imagery we use has been captured by varying sensors at varying times. To describe village pixels we compute phase-gradient, cornerness and color features at every pixel of the image. We apply feature selection methods to select salient features for discrimination of village pixels from the rest. We select only one cornerness feature at a particular scale having equivalent capability to discriminate the village pixels. The rest of the features need not to be computed and the feature computation module becomes very fast. Using the selected feature, we segment the image into two clusters by applying k-means++ algorithm. The cluster having larger cluster-center (according to the property of selected feature) is labeled as a village. A MATLAB tool is also built for marking the ground truth for large images with a minimal interaction. Experiments further elaborate effectiveness of work in practical applications especially in large images.
2021 International Conference on Innovative Computing (ICIC), 2021
developing countries are generally faced with several problems due to which their economy is most... more developing countries are generally faced with several problems due to which their economy is mostly at stake. Long term opportunities can play a vital role in increasing investments. CPEC is a great initiative taken by Pakistan and China for improving interest of investors for participation. This paper discusses timeline of CPEC project. Previous and ongoing projects are both discussed in the paper. The paper recommends to use Chinese social media for CPEC project. There is a breakthrough of different social media platforms in CPEC which is the main focus of this paper. A video bearer model is developed by the authors to make YouTube videos accessible for VKontakte (Vk) users which can give awareness to users about Chinese market trends related to CPEC. The paper is attractive for entrepreneurs who are interested in CPEC. Self-observance is used for getting results from different websites and some results are derived from vidIQ tool. This research is beneficial to entrepreneurs interested in investment and it is useful for providing consultancy to investors. Also, in the paper authors have observed the expected barriers..
2021 International Conference on Innovative Computing (ICIC), 2021
Software Requirement Engineering (RE) has been considered as the most significant part of softwar... more Software Requirement Engineering (RE) has been considered as the most significant part of software development life cycle (SDLC). It impacts the overall project progress and quality of the final product. Spending insufficient amount of time and effort in requirement engineering phase can increase the cost of errors in next phases of SDLC. Many approaches and techniques have been proposed by researchers so far, but all of them have not been practiced very widely in the industry. In order to further refine and improve requirement engineering process, problems faced in contemporary practice needs to be understood. General objective of this research is to identify and analyze requirement engineering practices in Pakistani Software Industry. Survey is used to gather data from local software industry. The analysis presents how frequently a particular type of RE practice is being used by local industry experts. The ultimate goal is to suggest best practices in requirement engineering and give recommendations to upcoming researchers regarding methods and techniques in this research area.
Sensors
Skin cancer is a deadly disease, and its early diagnosis enhances the chances of survival. Deep l... more Skin cancer is a deadly disease, and its early diagnosis enhances the chances of survival. Deep learning algorithms for skin cancer detection have become popular in recent years. A novel framework based on deep learning is proposed in this study for the multiclassification of skin cancer types such as Melanoma, Melanocytic Nevi, Basal Cell Carcinoma and Benign Keratosis. The proposed model is named as SCDNet which combines Vgg16 with convolutional neural networks (CNN) for the classification of different types of skin cancer. Moreover, the accuracy of the proposed method is also compared with the four state-of-the-art pre-trained classifiers in the medical domain named Resnet 50, Inception v3, AlexNet and Vgg19. The performance of the proposed SCDNet classifier, as well as the four state-of-the-art classifiers, is evaluated using the ISIC 2019 dataset. The accuracy rate of the proposed SDCNet is 96.91% for the multiclassification of skin cancer whereas, the accuracy rates for Resnet...
Journal of Personalized Medicine
Brain tumors are a deadly disease with a high mortality rate. Early diagnosis of brain tumors imp... more Brain tumors are a deadly disease with a high mortality rate. Early diagnosis of brain tumors improves treatment, which results in a better survival rate for patients. Artificial intelligence (AI) has recently emerged as an assistive technology for the early diagnosis of tumors, and AI is the primary focus of researchers in the diagnosis of brain tumors. This study provides an overview of recent research on the diagnosis of brain tumors using federated and deep learning methods. The primary objective is to explore the performance of deep and federated learning methods and evaluate their accuracy in the diagnosis process. A systematic literature review is provided, discussing the open issues and challenges, which are likely to guide future researchers working in the field of brain tumor diagnosis.
Multimedia Systems, 2022
Globally, coronavirus disease (COVID-19) has badly affected the medical system and economy. Somet... more Globally, coronavirus disease (COVID-19) has badly affected the medical system and economy. Sometimes, the deadly COVID-19 has the same symptoms as other chest diseases such as pneumonia and lungs cancer and can mislead the doctors in diagnosing coronavirus. Frontline doctors and researchers are working assiduously in finding the rapid and automatic process for the detection of COVID-19 at the initial stage, to save human lives. However, the clinical diagnosis of COVID-19 is highly subjective and variable. The objective of this study is to implement a multi-classification algorithm based on deep learning (DL) model for identifying the COVID-19, pneumonia, and lung cancer diseases from chest radiographs. In the present study, we have proposed a model with the combination of Vgg-19 and convolutional neural networks (CNN) named BDCNet and applied it on different publically available benchmark databases to diagnose the COVID-19 and other chest tract diseases. To the best of our knowledg...
IEEE Access, 2021
As rapid decision making in business organizations gain in popularity, the complexity and adaptab... more As rapid decision making in business organizations gain in popularity, the complexity and adaptability of extract, transform, and load (ETL) process of near real-time data warehousing has dramatically increased. The most important part of near real-time data warehouse is to feed new data from different data sources on near-real-time basis. However, this new data is not in the format of the data warehouse therefore, it needs to be transformed into the required format by using transformation algorithms which is essential part of ETL process. A semi-stream join algorithm is required to implement this transformation, for this purpose a HYBRIDJOIN (hybrid join) algorithm has been presented in the literature. However, major design issue with this algorithm is that it uses a single buffer to load the disk partitions and therefore, the algorithm has to wait until the next disk partition overwrites the exiting partition in the disk buffer. As the cost of loading disk partition into disk buffer is the major cost of overall algorithm processing cost, this leaves the performance of algorithm sub-optimal. Moreover, existing approaches only considering the oldest key join attributes for finding the matches with master data and maintaining the Queue of key join attribute. However, performance can be improved if recent and oldest attributes process in parallel. This article addresses the limitation of HYBRIDJOIN by presenting two optimized new algorithms named: Parallel-Hybrid Join (P-HYBRIDJOIN) and Hybrid Join with Queue and Stack (QaS-HYBRIDJOIN). Proposed algorithms aim to reduce major processing cost that is disk I/O as well as to increase number of matching stream tuples. Both of these algorithms perform significantly better in terms of throughput and number of matching tuples as compared to existing approaches. Performance analysis and cost model for proposed algorithms show the best performance using intermittent stream data under limited resources. INDEX TERMS Near-real-time data warehouse, semi-stream join, optimized hybrid join, queue and stack.
2019 International Conference on Innovative Computing (ICIC), 2019
Agile software development is taking over traditional methodologies. Agile methodologies provide ... more Agile software development is taking over traditional methodologies. Agile methodologies provide more benefits than traditional methodologies that's the reason why more software organizations, teams are making their transitions towards agile era. There are many flavors of agile methodologies available today. Organizations can choose them according to their needs. These methodologies include Scrum, eXtreme Programming (XP), Dynamic Systems Development Method (DSDM) and others. Agile methods especially target functional aspects of the software to be built, quality is their second priority. Software Quality is one of the major concerns for software organizations now a days. Reusability, on the other hand, is also important in terms of reducing cost to market, less time consumption in development and increased software productivity. Agile methods put a very little emphasis on these two highlighted points. In the paper, authors have proposed an effective, more reactive framework to increase the capabilities of agile to address reusability, documentation and ultimately quality concerns. Authors evaluated the proposed framework with the existing agile methodologies and the results show that the proposed framework improves quality better than existing agile methodologies.
IEEE Access, 2021
Web of things (WoT) is an improved and most promising infrastructure of the internet of things (I... more Web of things (WoT) is an improved and most promising infrastructure of the internet of things (IoT) which permits the smart things to not only integrate to the internet but also to the web. It allows the users to share and create content as well as provide capabilities for data aggregation and analysis through a network to become part of the World Wide Web (W3). Despite these advances, it has shown several security challenges that need to be addressed for the successful deployment of WoT on a commercially variable and large scale. In this paper, authors have analyzed the most noticeable security challenges related to WoT such as unauthorized access, eavesdropping, denial of service attack, tempering, and impersonating, through an analysis of already published empirical studies. Further, we have discussed some of the available mechanisms to overcome security related issues while taking into account the network size and mobility. Authors have used Threat analysis and attack modeling methods to inform the users about defensive measures and to prevent security threats from taking advantage of system flaws Authors have provided the necessary insight into how security can be improved by using certain existing mechanisms and algorithms. The findings of the study revealed that security mechanisms to secure WoT are still immature and future research is required to resolve these challenges. INDEX TERMS Web of things, Internet of Things, security challenges, security mechanisms, World Wide Web, security analysis, attack modeling.
Exploring the new avenues in the domain of video surveillance is a key aspect to maintain a secur... more Exploring the new avenues in the domain of video surveillance is a key aspect to maintain a secure environment by enabling several monitoring and security systems having ranges from home solution to border surveillance. Combining multiple cameras view to integrate one large view is far better than looking at each view individually. Car parking is a critical and time-consuming issue in congested cities. This study proposed a model to monitor and assist for car parking by stitching multiple videos and creating a 360 degree localized view. A complete model is proposed and steps are defined for each module including video acquisition, stitching and 360 degrees localized view. A single view is created from all individual cameras. When a car enters into a parking area, the driver is to be guided towards free slot by proposed monitoring and assistance system.
Public Elections are the best way to elect the government in democracy. Thus, it is the utmost re... more Public Elections are the best way to elect the government in democracy. Thus, it is the utmost responsibility of the state to organize non-fraudulent elections. With the advancement in technology we have an opportunity to switch our voting system from ballot paper to an electronic voting system. The Estonian voting system is one of the leading electronic voting systems which is still not perfect & need to improve its security & privacy features. Keeping in focus the privacy & transparency concerns this paper introduces a blockchain based decentralized electronic voting system for elections on large scale. The significant features of the proposed system are data integrity & transparency. Blockchain uses encryption & hashing to ensure the security of each vote. The scalability & verifiability in proposed system make the voting process more secured and reliable.
Agent Based modelling is widely used for presenting and evaluating a social phenomenon. Agent bas... more Agent Based modelling is widely used for presenting and evaluating a social phenomenon. Agent based modelling helps the researcher to analyze and evaluate a social model and its related hypothetical theories by simulating a real situation. This research presents a model for showing the behavior of an offender that is greatly influenced by volunteering of people on the offending tendencies. It is observed that how the offending behavior of someone urges others to do the same criminal act or violation of norms. And how can volunteering make the offender feel shameful of his doings and motivate others to volunteer in likewise situation in future. An agent based Model is presented and simulated to evaluate and validate the conceptualization of presented social dilemma. This model is simulated by asking some questions with exacting focus on the offending behavior of an agent. This study evaluates all the simulated results from the presented model to describe theoretical foundation spread...
Proceedings of the 2019 5th International Conference on Computer and Technology Applications, 2019
Many architectural patterns and styles are used for bringing in quality in software's such as... more Many architectural patterns and styles are used for bringing in quality in software's such as client-server, component-based, event-driven and data-centric architectures. Service-oriented architecture (SOA) is a new trend for improving the quality attributes of software such as interoperability and availability. Although, research studies claim that SOA adaption is widely used in practice, it is not very clear that is it used in the same way in under developed countries such as Pakistan. This research study analyzes the usage of SOA by the IT industry of Pakistan. In this paper, several opinions of professionals are collected from IT industry who belongs to different companies from all over the Pakistan. Questionnaires and semi-structured interviews helped as investigation tools for this research and the outcomes are analyzed on their responses. Results indicate that 76 % of the IT companies in Pakistan are using SOA. Most of the companies are using tool-based approach for development. Results also indicate a rising tendency of SOA adoption by Pakistan IT industry in upcoming years.
IEEE Access, 2020
Contribution: Recently, real-time data warehousing (DWH) and big data streaming have become ubiqu... more Contribution: Recently, real-time data warehousing (DWH) and big data streaming have become ubiquitous due to the fact that a number of business organizations are gearing up to gain competitive advantage. The capability of organizing big data in efficient manner to reach a business decision empowers data warehousing in terms of real-time stream processing. A systematic literature review for real-time stream processing systems is presented in this paper which rigorously look at the recent developments and challenges of real-time stream processing systems and can serve as a guide for the implementation of real-time stream processing framework for all shapes of data streams. Background: Published surveys and reviews either cover papers focusing on stream analysis in applications other than real-time DWH or focusing on extraction, transformation, loading (ETL) challenges for traditional DWH. This systematic review attempts to answer four specific research questions. Research Questions: 1)Which are the relevant publication channels for realtime stream processing research? 2) Which challenges have been faced during implementation of real-time stream processing? 3) Which approaches/tools have been reported to address challenges introduced at ETL stage while processing real-time stream for real-time DWH? 4) What evidence have been reported while addressing different challenges for processing real-time stream? Methodology: A systematic literature was conducted to compile studies related to publication channels targeting real-time stream processing/joins challenges and developments. Following a formal protocol, semi-automatic and manual searches were performed for work from 2011 to 2020 excluding research in traditional data warehousing. Of 679,547 papers selected for data extraction, 74 were retained after quality assessment. Findings: This systematic literature highlights implementation challenges along with developed approaches for real-time DWH and big data stream processing systems and provides their comparisons. This study found that there exists various algorithms for implementing real-time join processing at ETL stage for structured data whereas less work for un-structured data is found in this subject matter. INDEX TERMS Real-time stream processing, big data streaming, structured/un-structured data, ETL, systematic literature review.
International Journal of Advanced Computer Science and Applications, 2018
Internet of Things (IoT) referred to interconnected the world of things like physical devices, ca... more Internet of Things (IoT) referred to interconnected the world of things like physical devices, cars, sensors, home appliances, actuators and machines embedded with software at any time, any location. The increasing number of IoT devices facing challenges which are registration, integration, describing sensor, interoperability, semantics, security, discovery and searching. The current systems are suitable for limited number of devices. Our ecosystem change day by day which means we have billions and trillions of devices connecting to the Internet in future. One major challenge in current system is searching of suitable Smart Things from a millions or even billions number of devices in IoT. For the purpose of searching and indexing, some discovery methods and techniques are discussed and compared. Those techniques and methods are studied and find out the limitations and issued of the current system. Another challenge to searching the Smart Things is a variety of description models for describing the Smart Things. In this piece of work, a novel search engine is proposed to search the Smart Things with variety of description models. A web interface is implemented in this research with HTML, JSON and XML formats. The description models of Smart Things SensorML, SensorThings API and W3C JSON-LD are implemented in the current proposed system.
IEEE Access, 2019
Due to an increase in the number of devices, the Web of Things (WoT) has attracted a great deal o... more Due to an increase in the number of devices, the Web of Things (WoT) has attracted a great deal of attention and focus from researchers in the past few years. The ultimate goal of Web of Things is to build an ideal search engine where the user or even devices can find other devices anywhere and at any time for using the resources of other devices. The purpose of the paper is to identify and to present the current research on Web of Things. Additionally, the paper focuses on the research gap that currently exists and on future needs in the domain of WoT. In Author's opinion, the literature review presented in the paper will effectively help the researchers in finding resources in WoT as it highlights the research gap in the domain of Web of Things and searching resources in WoT. The results of the review indicate that the current challenges for the Web of Things are dynamic searching, scalability, data integration, intent-based searching, etc. The focus of this paper is on dynamic searching.
Complex & Intelligent Systems
Deep learning for image retrieval has been used in this era, but image retrieval with the highest... more Deep learning for image retrieval has been used in this era, but image retrieval with the highest accuracy is the biggest challenge, which still lacks auto-correlation for feature extraction and description. In this paper, a novel deep learning technique for achieving highly accurate results for image retrieval is proposed, which implements a convolutional neural network with auto-correlation, gradient computation, scaling, filter, and localization coupled with state-of-the-art content-based image retrieval methods. For this purpose, novel image features are fused with signatures produced by the VGG-16. In the initial step, images from rectangular neighboring key points are auto-correlated. The image smoothing is achieved by computing intensities according to the local gradient. The result of Gaussian approximation with the lowest scale and suppression is adjusted by the by-box filter with the standard deviation adjusted to the lowest scale. The parameterized images are smoothed at ...
Knowledge and Information Systems
Multimedia Tools and Applications
Coronavirus (COVID-19) has adversely harmed the healthcare system and economy throughout the worl... more Coronavirus (COVID-19) has adversely harmed the healthcare system and economy throughout the world. COVID-19 has similar symptoms as other chest disorders such as lung cancer (LC), pneumothorax, tuberculosis (TB), and pneumonia, which might mislead the clinical professionals in detecting a new variant of flu called coronavirus. This motivates us to design a model to classify multi-chest infections. A chest x-ray is the most ubiquitous disease diagnosis process in medical practice. As a result, chest x-ray examinations are the primary diagnostic tool for all of these chest infections. For the sake of saving human lives, paramedics and researchers are working tirelessly to establish a precise and reliable method for diagnosing the disease COVID-19 at an early stage. However, COVID-19's medical diagnosis is exceedingly idiosyncratic and varied. A multi-classification method based on the deep learning (DL) model is developed and tested in this work to automatically classify the COVID-19, LC, pneumothorax, TB, and pneumonia from chest x-ray images. COVID-19 and other chest tract disorders are diagnosed using a convolutional neural network (CNN) model called CDC Net that incorporates residual network thoughts and dilated convolution. For this study, we used this model in conjunction with publically available benchmark data to identify these diseases. For the first time, a single deep learning model has been used to diagnose five different chest ailments. In terms of classification accuracy, recall, precision, and f1-score, we compared the proposed model to three CNN-based pre-trained models, such as Vgg-19, ResNet-50, and inception v3. An AUC of 0.9953 was attained by the CDC Net when Multimedia Tools and Applications
2021 International Conference on Innovative Computing (ICIC), 2021
Automatic land cover classification through satellite imagery is an important remote sensing prob... more Automatic land cover classification through satellite imagery is an important remote sensing problem. Varying satellite-sensor’s characteristics reflect their own differences in the images and a sensor independent solution to the problem becomes difficult in general. Along with the sensor specific variations, the time at which the image is captured is yet another parameter. We propose an efficient method for village segmentation. The satellite imagery we use has been captured by varying sensors at varying times. To describe village pixels we compute phase-gradient, cornerness and color features at every pixel of the image. We apply feature selection methods to select salient features for discrimination of village pixels from the rest. We select only one cornerness feature at a particular scale having equivalent capability to discriminate the village pixels. The rest of the features need not to be computed and the feature computation module becomes very fast. Using the selected feature, we segment the image into two clusters by applying k-means++ algorithm. The cluster having larger cluster-center (according to the property of selected feature) is labeled as a village. A MATLAB tool is also built for marking the ground truth for large images with a minimal interaction. Experiments further elaborate effectiveness of work in practical applications especially in large images.
2021 International Conference on Innovative Computing (ICIC), 2021
developing countries are generally faced with several problems due to which their economy is most... more developing countries are generally faced with several problems due to which their economy is mostly at stake. Long term opportunities can play a vital role in increasing investments. CPEC is a great initiative taken by Pakistan and China for improving interest of investors for participation. This paper discusses timeline of CPEC project. Previous and ongoing projects are both discussed in the paper. The paper recommends to use Chinese social media for CPEC project. There is a breakthrough of different social media platforms in CPEC which is the main focus of this paper. A video bearer model is developed by the authors to make YouTube videos accessible for VKontakte (Vk) users which can give awareness to users about Chinese market trends related to CPEC. The paper is attractive for entrepreneurs who are interested in CPEC. Self-observance is used for getting results from different websites and some results are derived from vidIQ tool. This research is beneficial to entrepreneurs interested in investment and it is useful for providing consultancy to investors. Also, in the paper authors have observed the expected barriers..
2021 International Conference on Innovative Computing (ICIC), 2021
Software Requirement Engineering (RE) has been considered as the most significant part of softwar... more Software Requirement Engineering (RE) has been considered as the most significant part of software development life cycle (SDLC). It impacts the overall project progress and quality of the final product. Spending insufficient amount of time and effort in requirement engineering phase can increase the cost of errors in next phases of SDLC. Many approaches and techniques have been proposed by researchers so far, but all of them have not been practiced very widely in the industry. In order to further refine and improve requirement engineering process, problems faced in contemporary practice needs to be understood. General objective of this research is to identify and analyze requirement engineering practices in Pakistani Software Industry. Survey is used to gather data from local software industry. The analysis presents how frequently a particular type of RE practice is being used by local industry experts. The ultimate goal is to suggest best practices in requirement engineering and give recommendations to upcoming researchers regarding methods and techniques in this research area.
Sensors
Skin cancer is a deadly disease, and its early diagnosis enhances the chances of survival. Deep l... more Skin cancer is a deadly disease, and its early diagnosis enhances the chances of survival. Deep learning algorithms for skin cancer detection have become popular in recent years. A novel framework based on deep learning is proposed in this study for the multiclassification of skin cancer types such as Melanoma, Melanocytic Nevi, Basal Cell Carcinoma and Benign Keratosis. The proposed model is named as SCDNet which combines Vgg16 with convolutional neural networks (CNN) for the classification of different types of skin cancer. Moreover, the accuracy of the proposed method is also compared with the four state-of-the-art pre-trained classifiers in the medical domain named Resnet 50, Inception v3, AlexNet and Vgg19. The performance of the proposed SCDNet classifier, as well as the four state-of-the-art classifiers, is evaluated using the ISIC 2019 dataset. The accuracy rate of the proposed SDCNet is 96.91% for the multiclassification of skin cancer whereas, the accuracy rates for Resnet...
Journal of Personalized Medicine
Brain tumors are a deadly disease with a high mortality rate. Early diagnosis of brain tumors imp... more Brain tumors are a deadly disease with a high mortality rate. Early diagnosis of brain tumors improves treatment, which results in a better survival rate for patients. Artificial intelligence (AI) has recently emerged as an assistive technology for the early diagnosis of tumors, and AI is the primary focus of researchers in the diagnosis of brain tumors. This study provides an overview of recent research on the diagnosis of brain tumors using federated and deep learning methods. The primary objective is to explore the performance of deep and federated learning methods and evaluate their accuracy in the diagnosis process. A systematic literature review is provided, discussing the open issues and challenges, which are likely to guide future researchers working in the field of brain tumor diagnosis.
Multimedia Systems, 2022
Globally, coronavirus disease (COVID-19) has badly affected the medical system and economy. Somet... more Globally, coronavirus disease (COVID-19) has badly affected the medical system and economy. Sometimes, the deadly COVID-19 has the same symptoms as other chest diseases such as pneumonia and lungs cancer and can mislead the doctors in diagnosing coronavirus. Frontline doctors and researchers are working assiduously in finding the rapid and automatic process for the detection of COVID-19 at the initial stage, to save human lives. However, the clinical diagnosis of COVID-19 is highly subjective and variable. The objective of this study is to implement a multi-classification algorithm based on deep learning (DL) model for identifying the COVID-19, pneumonia, and lung cancer diseases from chest radiographs. In the present study, we have proposed a model with the combination of Vgg-19 and convolutional neural networks (CNN) named BDCNet and applied it on different publically available benchmark databases to diagnose the COVID-19 and other chest tract diseases. To the best of our knowledg...
IEEE Access, 2021
As rapid decision making in business organizations gain in popularity, the complexity and adaptab... more As rapid decision making in business organizations gain in popularity, the complexity and adaptability of extract, transform, and load (ETL) process of near real-time data warehousing has dramatically increased. The most important part of near real-time data warehouse is to feed new data from different data sources on near-real-time basis. However, this new data is not in the format of the data warehouse therefore, it needs to be transformed into the required format by using transformation algorithms which is essential part of ETL process. A semi-stream join algorithm is required to implement this transformation, for this purpose a HYBRIDJOIN (hybrid join) algorithm has been presented in the literature. However, major design issue with this algorithm is that it uses a single buffer to load the disk partitions and therefore, the algorithm has to wait until the next disk partition overwrites the exiting partition in the disk buffer. As the cost of loading disk partition into disk buffer is the major cost of overall algorithm processing cost, this leaves the performance of algorithm sub-optimal. Moreover, existing approaches only considering the oldest key join attributes for finding the matches with master data and maintaining the Queue of key join attribute. However, performance can be improved if recent and oldest attributes process in parallel. This article addresses the limitation of HYBRIDJOIN by presenting two optimized new algorithms named: Parallel-Hybrid Join (P-HYBRIDJOIN) and Hybrid Join with Queue and Stack (QaS-HYBRIDJOIN). Proposed algorithms aim to reduce major processing cost that is disk I/O as well as to increase number of matching stream tuples. Both of these algorithms perform significantly better in terms of throughput and number of matching tuples as compared to existing approaches. Performance analysis and cost model for proposed algorithms show the best performance using intermittent stream data under limited resources. INDEX TERMS Near-real-time data warehouse, semi-stream join, optimized hybrid join, queue and stack.
2019 International Conference on Innovative Computing (ICIC), 2019
Agile software development is taking over traditional methodologies. Agile methodologies provide ... more Agile software development is taking over traditional methodologies. Agile methodologies provide more benefits than traditional methodologies that's the reason why more software organizations, teams are making their transitions towards agile era. There are many flavors of agile methodologies available today. Organizations can choose them according to their needs. These methodologies include Scrum, eXtreme Programming (XP), Dynamic Systems Development Method (DSDM) and others. Agile methods especially target functional aspects of the software to be built, quality is their second priority. Software Quality is one of the major concerns for software organizations now a days. Reusability, on the other hand, is also important in terms of reducing cost to market, less time consumption in development and increased software productivity. Agile methods put a very little emphasis on these two highlighted points. In the paper, authors have proposed an effective, more reactive framework to increase the capabilities of agile to address reusability, documentation and ultimately quality concerns. Authors evaluated the proposed framework with the existing agile methodologies and the results show that the proposed framework improves quality better than existing agile methodologies.
IEEE Access, 2021
Web of things (WoT) is an improved and most promising infrastructure of the internet of things (I... more Web of things (WoT) is an improved and most promising infrastructure of the internet of things (IoT) which permits the smart things to not only integrate to the internet but also to the web. It allows the users to share and create content as well as provide capabilities for data aggregation and analysis through a network to become part of the World Wide Web (W3). Despite these advances, it has shown several security challenges that need to be addressed for the successful deployment of WoT on a commercially variable and large scale. In this paper, authors have analyzed the most noticeable security challenges related to WoT such as unauthorized access, eavesdropping, denial of service attack, tempering, and impersonating, through an analysis of already published empirical studies. Further, we have discussed some of the available mechanisms to overcome security related issues while taking into account the network size and mobility. Authors have used Threat analysis and attack modeling methods to inform the users about defensive measures and to prevent security threats from taking advantage of system flaws Authors have provided the necessary insight into how security can be improved by using certain existing mechanisms and algorithms. The findings of the study revealed that security mechanisms to secure WoT are still immature and future research is required to resolve these challenges. INDEX TERMS Web of things, Internet of Things, security challenges, security mechanisms, World Wide Web, security analysis, attack modeling.
Exploring the new avenues in the domain of video surveillance is a key aspect to maintain a secur... more Exploring the new avenues in the domain of video surveillance is a key aspect to maintain a secure environment by enabling several monitoring and security systems having ranges from home solution to border surveillance. Combining multiple cameras view to integrate one large view is far better than looking at each view individually. Car parking is a critical and time-consuming issue in congested cities. This study proposed a model to monitor and assist for car parking by stitching multiple videos and creating a 360 degree localized view. A complete model is proposed and steps are defined for each module including video acquisition, stitching and 360 degrees localized view. A single view is created from all individual cameras. When a car enters into a parking area, the driver is to be guided towards free slot by proposed monitoring and assistance system.
Public Elections are the best way to elect the government in democracy. Thus, it is the utmost re... more Public Elections are the best way to elect the government in democracy. Thus, it is the utmost responsibility of the state to organize non-fraudulent elections. With the advancement in technology we have an opportunity to switch our voting system from ballot paper to an electronic voting system. The Estonian voting system is one of the leading electronic voting systems which is still not perfect & need to improve its security & privacy features. Keeping in focus the privacy & transparency concerns this paper introduces a blockchain based decentralized electronic voting system for elections on large scale. The significant features of the proposed system are data integrity & transparency. Blockchain uses encryption & hashing to ensure the security of each vote. The scalability & verifiability in proposed system make the voting process more secured and reliable.
Agent Based modelling is widely used for presenting and evaluating a social phenomenon. Agent bas... more Agent Based modelling is widely used for presenting and evaluating a social phenomenon. Agent based modelling helps the researcher to analyze and evaluate a social model and its related hypothetical theories by simulating a real situation. This research presents a model for showing the behavior of an offender that is greatly influenced by volunteering of people on the offending tendencies. It is observed that how the offending behavior of someone urges others to do the same criminal act or violation of norms. And how can volunteering make the offender feel shameful of his doings and motivate others to volunteer in likewise situation in future. An agent based Model is presented and simulated to evaluate and validate the conceptualization of presented social dilemma. This model is simulated by asking some questions with exacting focus on the offending behavior of an agent. This study evaluates all the simulated results from the presented model to describe theoretical foundation spread...
Proceedings of the 2019 5th International Conference on Computer and Technology Applications, 2019
Many architectural patterns and styles are used for bringing in quality in software's such as... more Many architectural patterns and styles are used for bringing in quality in software's such as client-server, component-based, event-driven and data-centric architectures. Service-oriented architecture (SOA) is a new trend for improving the quality attributes of software such as interoperability and availability. Although, research studies claim that SOA adaption is widely used in practice, it is not very clear that is it used in the same way in under developed countries such as Pakistan. This research study analyzes the usage of SOA by the IT industry of Pakistan. In this paper, several opinions of professionals are collected from IT industry who belongs to different companies from all over the Pakistan. Questionnaires and semi-structured interviews helped as investigation tools for this research and the outcomes are analyzed on their responses. Results indicate that 76 % of the IT companies in Pakistan are using SOA. Most of the companies are using tool-based approach for development. Results also indicate a rising tendency of SOA adoption by Pakistan IT industry in upcoming years.
IEEE Access, 2020
Contribution: Recently, real-time data warehousing (DWH) and big data streaming have become ubiqu... more Contribution: Recently, real-time data warehousing (DWH) and big data streaming have become ubiquitous due to the fact that a number of business organizations are gearing up to gain competitive advantage. The capability of organizing big data in efficient manner to reach a business decision empowers data warehousing in terms of real-time stream processing. A systematic literature review for real-time stream processing systems is presented in this paper which rigorously look at the recent developments and challenges of real-time stream processing systems and can serve as a guide for the implementation of real-time stream processing framework for all shapes of data streams. Background: Published surveys and reviews either cover papers focusing on stream analysis in applications other than real-time DWH or focusing on extraction, transformation, loading (ETL) challenges for traditional DWH. This systematic review attempts to answer four specific research questions. Research Questions: 1)Which are the relevant publication channels for realtime stream processing research? 2) Which challenges have been faced during implementation of real-time stream processing? 3) Which approaches/tools have been reported to address challenges introduced at ETL stage while processing real-time stream for real-time DWH? 4) What evidence have been reported while addressing different challenges for processing real-time stream? Methodology: A systematic literature was conducted to compile studies related to publication channels targeting real-time stream processing/joins challenges and developments. Following a formal protocol, semi-automatic and manual searches were performed for work from 2011 to 2020 excluding research in traditional data warehousing. Of 679,547 papers selected for data extraction, 74 were retained after quality assessment. Findings: This systematic literature highlights implementation challenges along with developed approaches for real-time DWH and big data stream processing systems and provides their comparisons. This study found that there exists various algorithms for implementing real-time join processing at ETL stage for structured data whereas less work for un-structured data is found in this subject matter. INDEX TERMS Real-time stream processing, big data streaming, structured/un-structured data, ETL, systematic literature review.
International Journal of Advanced Computer Science and Applications, 2018
Internet of Things (IoT) referred to interconnected the world of things like physical devices, ca... more Internet of Things (IoT) referred to interconnected the world of things like physical devices, cars, sensors, home appliances, actuators and machines embedded with software at any time, any location. The increasing number of IoT devices facing challenges which are registration, integration, describing sensor, interoperability, semantics, security, discovery and searching. The current systems are suitable for limited number of devices. Our ecosystem change day by day which means we have billions and trillions of devices connecting to the Internet in future. One major challenge in current system is searching of suitable Smart Things from a millions or even billions number of devices in IoT. For the purpose of searching and indexing, some discovery methods and techniques are discussed and compared. Those techniques and methods are studied and find out the limitations and issued of the current system. Another challenge to searching the Smart Things is a variety of description models for describing the Smart Things. In this piece of work, a novel search engine is proposed to search the Smart Things with variety of description models. A web interface is implemented in this research with HTML, JSON and XML formats. The description models of Smart Things SensorML, SensorThings API and W3C JSON-LD are implemented in the current proposed system.
IEEE Access, 2019
Due to an increase in the number of devices, the Web of Things (WoT) has attracted a great deal o... more Due to an increase in the number of devices, the Web of Things (WoT) has attracted a great deal of attention and focus from researchers in the past few years. The ultimate goal of Web of Things is to build an ideal search engine where the user or even devices can find other devices anywhere and at any time for using the resources of other devices. The purpose of the paper is to identify and to present the current research on Web of Things. Additionally, the paper focuses on the research gap that currently exists and on future needs in the domain of WoT. In Author's opinion, the literature review presented in the paper will effectively help the researchers in finding resources in WoT as it highlights the research gap in the domain of Web of Things and searching resources in WoT. The results of the review indicate that the current challenges for the Web of Things are dynamic searching, scalability, data integration, intent-based searching, etc. The focus of this paper is on dynamic searching.