Fayyaz Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Fayyaz Ali has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Irfan Ali Kandhro
Department of Computer Science, Sindh Madressatul Islam University, Karachi, Pakistan
2 shared publications - Abdullah Ayub Khan
Department of Computer Science Bahria University Karachi Campus Karachi Pakistan
1 shared publication - Abeer Javed Syed
Department of Software engineering, SSUET, Karachi
1 shared publication - Ali Abbas
School of Management, Xiamen University, Xiamen, China
1 shared publication Anwar Ali Sanjrani
1 shared publication- Asadullah Kehar
Institute of Computer Science, Shah Abdul Latif University, Khairpur, Pakistan
1 shared publication
Latest Publications
- Open Access
- 8 May 2024
- Published by VFAST Research Platform in VAWKUM Transactions on Computer Sciences
- Vol. 14 (1) , 110-124
FedSecureNLP: an Advanced Federated Learning approach for privacy-preserving and secure Ecommerce NLP System
This research presents an advanced Federated Learning approach for privacy-preserving and secure Ecommerce NLP System. Recently, the amount of information is growing very fast, and its importance is also rising quickly. Today, businesses handle huge volumes of data, like emails, which are often key to how they run day to day. It's difficult to find useful information from all this data and keeping it safe is a big worry. Keeping data secure is very important for protecting the trust of an online store and making customers feel safe when they make purchases. Hence, in this paper we have developed a privacy-preserving and secure FedSecureNLP system for text summarization, sentiment analysis and question answering. Within the FL configuration, the local training text summarization, sentiment predication and question answering is performed autonomously on each node local dataset. The Bidirectional Encoder Representations from Transformers (BERT) tokenization is used in the model to create tokens and extract term from amazon review data, after that, hierarchical deep learning for text (HDLTex) is used to predict sentiment rating. The Deep learning network (DeepCNN) is then used to do extractive summarization. Random multimodal deep learning (RMDL) is used for QA prediction. The QA model has different training and testing steps in the Module. During the evaluation phase, pretrained RMDL process the input query and semantically analyzed and generates relevant response. In this case FCDVO is designed to adjust the HDLTex, Deep CNN, and RMDL hyperparameters. The precision, recall, F-measure and Root Mean Square Error (RMSE) of the System that presented were 0.088, 92.896%, 92.481% and 92.688% respectively
- 8 May 2024
- Published by VFAST Research Platform in VAWKUM Transactions on Computer Sciences
- Vol. 14 (1) , 110-124
Open AccessFedSecureNLP: an Advanced Federated Learning approach for privacy-preserving and secure Ecommerce NLP System
This research presents an advanced Federated Learning approach for privacy-preserving and secure Ecommerce NLP System. Recently, the amount of information is growing very fast, and its importance is also rising quickly. Today, businesses handle huge volumes of data, like emails, which are often key to how they run day to day. It's difficult to find useful information from all this data and keeping it safe is a big worry. Keeping data secure is very important for protecting the trust of an online store and making customers feel safe when they make purchases. Hence, in this paper we have developed a privacy-preserving and secure FedSecureNLP system for text summarization, sentiment analysis and question answering. Within the FL configuration, the local training text summarization, sentiment predication and question answering is performed autonomously on each node local dataset. The Bidirectional Encoder Representations from Transformers (BERT) tokenization is used in the model to create tokens and extract term from amazon review data, after that, hierarchical deep learning for text (HDLTex) is used to predict sentiment rating. The Deep learning network (DeepCNN) is then used to do extractive summarization. Random multimodal deep learning (RMDL) is used for QA prediction. The QA model has different training and testing steps in the Module. During the evaluation phase, pretrained RMDL process the input query and semantically analyzed and generates relevant response. In this case FCDVO is designed to adjust the HDLTex, Deep CNN, and RMDL hyperparameters. The precision, recall, F-measure and Root Mean Square Error (RMSE) of the System that presented were 0.088, 92.896%, 92.481% and 92.688% respectively
- Open Access
- 13 November 2023
- Published by VFAST Research Platform in VFAST Transactions on Software Engineering
- Vol. 11 (4) , 105-123
Optimizing the Efficiency of Web Mining through Comparative Web Ranking Algorithms
Millions of web pages carrying massive amounts of data make up the World Wide Web. Real-time data has been generated on a wide scale on the websites. However, not every piece of data is relevant to the user. While scouring the web for information, a user may come upon a web page that contains irrelevant or incomplete information. As a response, search engines can alleviate this issue by displaying the most relevant pages. Two web page ranking algorithms are proposed in this study along with the Dijkstra algorithm; the PageRank algorithm and the Weighted PageRank algorithm. The algorithms are used to evaluate a web page's importance or relevancy within a network, such as the Internet. PageRank evaluates a page's value based on the quantity and quality of links leading to it. It is commonly utilized by nearly all search engines around the world to rank web pages in order of relevance. This algorithm is used by Google, the most widespread Internet search engine. In the process of Web mining, page rank is quite weighty. The most important component of marketing is online use mining, which investigates how people browse and operate a business on a company's website. The study presents two proposed models that try to optimize web links and improve search engine results relevancy for users.
- 13 November 2023
- Published by VFAST Research Platform in VFAST Transactions on Software Engineering
- Vol. 11 (4) , 105-123
Open AccessOptimizing the Efficiency of Web Mining through Comparative Web Ranking Algorithms
Millions of web pages carrying massive amounts of data make up the World Wide Web. Real-time data has been generated on a wide scale on the websites. However, not every piece of data is relevant to the user. While scouring the web for information, a user may come upon a web page that contains irrelevant or incomplete information. As a response, search engines can alleviate this issue by displaying the most relevant pages. Two web page ranking algorithms are proposed in this study along with the Dijkstra algorithm; the PageRank algorithm and the Weighted PageRank algorithm. The algorithms are used to evaluate a web page's importance or relevancy within a network, such as the Internet. PageRank evaluates a page's value based on the quantity and quality of links leading to it. It is commonly utilized by nearly all search engines around the world to rank web pages in order of relevance. This algorithm is used by Google, the most widespread Internet search engine. In the process of Web mining, page rank is quite weighty. The most important component of marketing is online use mining, which investigates how people browse and operate a business on a company's website. The study presents two proposed models that try to optimize web links and improve search engine results relevancy for users.
- Open Access
- 24 March 2022
- Published by Sciencedomain International in Journal of Pharmaceutical Research International
- p. 19-30
Smart Health Monitoring System (SHMS) an Enabling Technology for Patient Care
Health Monitoring System is a sophisticating technology and another way to the normal/regular management of the health of the patient. This Health Monitoring Mobile Application is a contribution from our side to the public and to the overall health industry in Pakistan. With the help of Health mobile application, the users will be able to store their medical records, prescriptions and retrieve them later. The users can store and keep track of their vital readings (heart rate, blood pressure, fasting glucose, random glucose). The mobile application also shows hospitals that are nearby in case the user wants to avail of any medical help. An important feature of the application is the symptoms-based disease prediction, the user selects the symptoms which he has and then the application will name certain diseases that match those symptoms based on relevant algorithms. The major advances and issues have been discussed, and as well as potential tasks to health monitoring will be identified and evaluated.
- 24 March 2022
- Published by Sciencedomain International in Journal of Pharmaceutical Research International
- p. 19-30
Open AccessSmart Health Monitoring System (SHMS) an Enabling Technology for Patient Care
Health Monitoring System is a sophisticating technology and another way to the normal/regular management of the health of the patient. This Health Monitoring Mobile Application is a contribution from our side to the public and to the overall health industry in Pakistan. With the help of Health mobile application, the users will be able to store their medical records, prescriptions and retrieve them later. The users can store and keep track of their vital readings (heart rate, blood pressure, fasting glucose, random glucose). The mobile application also shows hospitals that are nearby in case the user wants to avail of any medical help. An important feature of the application is the symptoms-based disease prediction, the user selects the symptoms which he has and then the application will name certain diseases that match those symptoms based on relevant algorithms. The major advances and issues have been discussed, and as well as potential tasks to health monitoring will be identified and evaluated.