- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Text and Document Classification Technologies
- Web Data Mining and Analysis
- Software System Performance and Reliability
- Natural Language Processing Techniques
- Advanced Software Engineering Methodologies
- Crime, Deviance, and Social Control
- Water Systems and Optimization
- Media Influence and Health
- Blockchain Technology Applications and Security
- Handwritten Text Recognition Techniques
- AI in cancer detection
- Model-Driven Software Engineering Techniques
- User Authentication and Security Systems
- Smart Parking Systems Research
- IoT and GPS-based Vehicle Safety Systems
- Child Development and Education
- Cybersecurity and Cyber Warfare Studies
- Interactive and Immersive Displays
- Evolutionary Algorithms and Applications
- Cutaneous Melanoma Detection and Management
- Service-Oriented Architecture and Web Services
- Distributed systems and fault tolerance
University of Lahore
2018-2023
Universiti Sains Malaysia
2015-2022
Machine learning can be used to automate a wide range of tasks. Smart buildings, which use the Internet Things (IoT) connect building operations, enable activities, such as monitoring temperature, safety, and maintenance, for easier controlling via mobile devices computers. buildings are becoming core aspects in larger system integrations IoT is increasingly widespread. The plays an important role smart provides facilities that improve human security by using effective technology-based...
Feature selection represents an essential pre-processing step for a wide range of Machine Learning approaches. Datasets typically contain irrelevant features that may negatively affect the classifier performance. A feature selector can reduce number these and maximise accuracy. This paper proposes Dynamic Butterfly Optimization Algorithm (DBOA) as improved variant to (BOA) problems. BOA one most recently proposed optimization algorithms. has demonstrated its ability solve different types...
E-commerce business is becoming more and popular as the number of customers shopping online increasing every day. Companies ask their to review products services offered by them over websites. For big companies, reviews could be in thousands. So it almost impossible for any company read these manually find out whether liked product or not. Many techniques have been proposed sentiment classification reviews. In this paper we are proposing rule-based hybrid approach which exploits sequential...
Aspect extraction or opinion target is the key task of sentiment analysis, which aims to identify targets people’s sentiments. This most important aspect-based analysis as without aspects, there no much use extracted opinions. Recent approaches have shown significance dependency-based rules for given task. These are heavily dependent on dependency parser and generated with help grammatical rules. In this article, we proposing learn from user’s behaviour relation among aspects The sequential...
ABSTRACT A simplified Multi‐Objective Genetic Algorithm Optimization Model (MOM‐GA) for canal scheduling under unequal flow rates of distributary canals is presented in this paper. This MOM‐GA was designed dynamic rotational with two objectives: to reduce fluctuations superior canals, and seepage losses systems. model programmed MATLAB using its genetic algorithm functions. Application demonstrated a case study the Nanguan Main Canal system (NMC) Gaoyou Irrigation Area, China. The results...
Aspect or feature extraction, from online customer reviews, is the key task of aspect-based sentiment analysis. This aims to extract fine-grained aspects which a challenging task. Most early work focused on extraction subjective associated with some opinion words but very few have objective aspects. These can affect overall performance aspect resulting in wrong results. In this paper, we proposed sequential pattern-based approach detect such are nature. We defined several patterns, basis...
During the last two decades, sentiment analysis, also known as opinion mining, has become one of most explored research areas in Natural Language Processing (NLP) and data mining. Sentiment analysis focuses on sentiments or opinions consumers expressed over social media different web sites. Due to exposure Internet, attracted vast numbers researchers globe. A large amount been conducted English, Chinese, other languages used worldwide. However, Roman Urdu neglected despite being third...
In Natural Language Processing (NLP), topic modeling is the technique to extract abstract information from documents with huge amount of text. This leads towards identification topics in document. One way retrieve keyphrase extraction. Keyphrases are a set terms which represent high level description Different techniques extraction for prediction have been proposed multiple languages i.e. English, Arabic, etc. However, this area needs be explored other e.g. Urdu. Therefore, paper, novel...
In the current era of internet, people use online media for conversation, discussion, chatting, and other similar purposes. Analysis such material where more than one person is involved has a spate challenge as compared to text analysis tasks. There are several approaches identify users’ emotions from conversational English language, however regional or low resource languages have been neglected. The Urdu language them despite being used by millions users across globe, with best our...
Opinion target or aspect extraction is the key task of aspect-based sentiment analysis. This focuses on targeted words phrases against which a user has expressed his/her opinion. Although, opinion been studied extensively in English language domain, with notable work other languages such as Chinese, Arabic etc., regional have neglected. One reasons lack resources and available texts for these languages. Urdu one, millions native non-native speakers across globe. In this paper, domain focused...
Fault-tolerance technique enables a system or application to continue working even if some fault /error occurs in system. Therefore, it is vital choose appropriate tolerant best suited our application. In case of real-time embedded systems space project, the importance such techniques becomes more critical. applications, there minor no possibility maintenance and faults occurrence may lead serious consequences terms partial complete mission failure. This paper describes comparison various...
Cyber-physical systems (CPS) are composed of software and hardware components. Many such (e.g., IoT based systems) created by composing existing together. Some these critical nature, e.g., emergency or disaster management systems. In general, component-based development (CBD) is a useful approach for constructing pre-built tested However, systems, method must provide ways to verify the partial system at different stages construction process. this paper, architectures, we propose two styles:...
Malignant melanoma is considered one of the deadliest skin diseases if ignored without treatment. The mortality rate caused by more than two times that other malignancy diseases. These facts encourage computer scientists to find automated methods discover cancers. Nowadays, analysis images widely used assistant physicians first stage disease automatically. One challenges science researchers faced when developing such a system un-clarity existing images, as noise like shadows, low contrast,...