A5009459014- Distributed and Parallel Computing Systems
- Scientific Computing and Data Management
- Virus-based gene therapy research
- Cloud Computing and Resource Management
- Pluripotent Stem Cells Research
- Animal Genetics and Reproduction
- Head and Neck Cancer Studies
- Oral and Maxillofacial Pathology
- Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- IoT and Edge/Fog Computing
- Oral Health Pathology and Treatment
- Data Mining Algorithms and Applications
- Network Security and Intrusion Detection
- Telemedicine and Telehealth Implementation
- Software System Performance and Reliability
- Advanced Data Storage Technologies
- Data Stream Mining Techniques
- COVID-19 diagnosis using AI
- Mobile Health and mHealth Applications
- Advanced Database Systems and Queries
- Mobile Learning in Education
- Data Management and Algorithms
- Internet Traffic Analysis and Secure E-voting
- Context-Aware Activity Recognition Systems
University of Malaya
2014-2025
Information Technology University
2007-2015
University of Edinburgh
2009-2013
Research on big data analytics is entering in the new phase called fast where multiple gigabytes of arrive systems every second. Modern collect inherently complex streams due to volume, velocity, value, variety, variability, and veracity acquired consequently give rise 6Vs data. The reduced relevant are perceived be more useful than collecting raw, redundant, inconsistent, noisy Another perspective for reduction that million variables datasets cause curse dimensionality which requires...
Over the past few years, Internet applications have become more advanced and widely used. This has increased need for networks to be secured. Intrusion detection systems (IDSs), which employ artificial intelligence (AI) methods, are vital ensuring network security. As a branch of AI, deep learning (DL) algorithms now effectively applied in IDSs. Among neural networks, convolutional (CNN) is well-known structure designed process complex data. The CNN overcomes typical limitations conventional...
The staggering growth in smartphone and wearable device use has led to a massive scale generation of personal (user-specific) data. To explore, analyze, extract useful information knowledge from the deluge data, one leverage these devices as data-mining platforms ubiquitous, pervasive, big data environments. This study presents ecosystem where all computational resources, communication facilities, storage management systems are available user proximity. An extensive review on recent...
The drug discovery and development pipeline is a long arduous process that inevitably hampers rapid development. Therefore, strategies to improve the efficiency of are urgently needed enable effective drugs enter clinic. Precision medicine has demonstrated genetic features cancer cells can be used for predicting response, emerging evidence suggest gene-drug connections could predicted more accurately by exploring cumulative effects many genes simultaneously.We developed DeSigN, web-based...
Background: Up to 86% of oral cancer (OC) patients present at the late stage where survival is dismal. Limited access specialist diagnosis a significant factor for presentation. The increasing use smartphones presents an opportunity digital technology facilitate early detection OC. Aim: To evaluate feasibility using Mobile Mouth Screening Anywhere (MeMoSA®) Methods: A mobile phone app named MeMoSA was developed and integrating this documentation lesions, communication between dentists...
Modern scientific collaborations have opened up the opportunity of solving complex problems that involve multi-disciplinary expertise and large-scale computational experiments. These experiments usually large amounts data are located in distributed repositories running various software systems, managed by different organisations. A common strategy to make more manageable is executing processing steps as a workflow. In this paper, we look into implementation fine-grained data-flow between...
Background During the COVID-19 pandemic, there was an urgent need to develop automated symptom monitoring system reduce burden on health care and provide better self-monitoring at home. Objective This paper aimed describe development process of Symptom Monitoring System (CoSMoS), which consists a self-monitoring, algorithm-based Telegram bot teleconsultation system. We all essential steps from clinical perspective our technical approach in designing, developing, integrating into practice...
Abstract Objective To evaluate the accuracy of MeMoSA®, a mobile phone application to review images oral lesions in identifying cancers and potentially malignant disorders requiring referral. Subjects Methods A prospective study 355 participants, including 280 with lesions/variants was conducted. Adults aged ≥18 treated at tertiary referral centres were included. Images cavity taken using MeMoSA®. The identification presence lesion/variant decision made MeMoSA® compared clinical examination,...
Stream based data processing model is proven to be an established method optimize data-intensive applications. Data-intensive applications involve movement of huge amount between execution nodes that incurs large costs. Data-streaming improves the performance such In stream-based model, usually measured by throughput and latency. Optimization these metrics in heterogeneous computing environment becomes more challenging due difference capacity variations transfer capability communication...
The significant development of Internet applications over the past 10 years has resulted in rising necessity for information network to be secured. An intrusion detection system is a fundamental infrastructure defense that must able adapt ever-evolving threat landscape and identify new attacks have low false alarm. Researchers developed several supervised as well unsupervised methods from data mining machine learning disciplines so anomalies can detected reliably. As an aspect learning, deep...
This paper presents the rationale for a new architecture to support significant increase in scale of data integration and mining. It proposes composition into one framework (1) mining (2) access integration. We name combined activity DMI. supports enactment DMI processes across heterogeneous distributed resources services. posits that useful division can be made between facilities established definition computational infrastructure provided enact processes. Communication those two divisions...
Cloud computing has taken the IT and business world by storm through its cost savings quick-and-easy adoption. Currently, fixed price model is dominating pricing schemes in cloud market. However, this unable to reflect current market needs for as number of provider user increases. As a result, dynamic scheme emerged an attractive strategy better cope with unpredictable demand. This paper proposed that provides fairness among service providers multi-cloud environment. The adjusts accordingly...
Wearable devices and Smartphones generate huge data streams in pervasive ubiquitous environments. Traditionally, big systems collect all the at a central processing system (DPS). These silos are further analyzed to approximated patterns for different application areas. This approach has one-sided utility (i.e. end) but two main side-effects that lead towards user's dissatisfaction extra computational costs. effects are: 1) since is being collected DPS, user privacy compromised 2) collection...
The development of software has always been characterized by parameters that possess certain level fuzziness. This requires some degree uncertainty be introduced in the models, order to make models realistic. Fuzzy logic fares well this area. Many problems existing effort estimation can solved incorporating fuzzy logic. Besides, had combined with algorithmic, non-algorithmic as a combination them deal inherent issues. paper also described an enhanced model for effort. (FLECE) possesses...