- Rehmanedit
Stemmer is a language processing tool that has been widely used in many artificial intelligence applications for removing affixes in a word such as prefixes, infixes, and suffixes to generate the root word. This study designs an algorithm... more
Stemmer is a language processing tool that has been widely used in many artificial intelligence applications for removing affixes in a word such as prefixes, infixes, and suffixes to generate the root word. This study designs an algorithm and develops a Malay language stemmer. It is given that most of Malay language stemmers have problems in stemming, as they tended to have dependencies on online dictionaries, which return false results during stemming. It is given that the complexity of affixes in Malay words is higher than that of English words. Therefore, an offline dictionary of 9,512 words is introduced in this study to handle the ambiguity when stemming Malay words. Each step the algorithm first checks the word in the local dictionary as a root word, otherwise process the word. The five steps are stem-extra-suffix, stem-plural, stem-infix, stem-prefix, and stem-suffix. The affixes rules are extracted from Kamus Tatabahasa, and Kamus Dewan (4th Ed) is used to confirm the accura...
Research Interests:
New generation is the future of every nation, but dyslexia which is a learning disability is spoiling the new generation. Most experts are using manual techniques to diagnose dyslexia. Machine learning algorithms are capable enough to... more
New generation is the future of every nation, but dyslexia which is a learning disability is spoiling the new generation. Most experts are using manual techniques to diagnose dyslexia. Machine learning algorithms are capable enough to learn the knowledge of experts and intelligently diagnose and classify dyslexics. This research proposes such a machine learning based diagnostic and classification system. The system is trained by human expert classified data of 857 school children scores in various tests. The data was collected in another fundamental research of designing special tests for dyslexics. Twenty-fifth percentile was used as threshold. The scores equal to the threshold and below were marked as indicators of children who were likely to have dyslexia while the scores above the threshold were considered to be indicators of children who were non-dyslexic. The system has three components: the diagnostic module is a pre-screening application that can be used by experts, trained ...
Research Interests:
Research Interests:
The world has suffered a critical shortage of Personal Protective Equipment (PPE) during the pandemic of COVID19 for medical staffs, the front liners. Like the whole world, Malaysia also imposed the stay-at-home and Movement Control Order... more
The world has suffered a critical shortage of Personal Protective Equipment (PPE) during the pandemic of COVID19 for medical staffs, the front liners. Like the whole world, Malaysia also imposed the stay-at-home and Movement Control Order (MCO) to break the chain of infections and flatten the curve of cases. The supply of PPE became a challenge during the lock down. There have been joined efforts from various parties stepping up, with different ways to help the production process of these key equipment but mostly focus on PPTs for male. Another challenge was face mask for Muslims leady health workers who wear hijab. This paper is about how to overcome these challenges and designed a novel face mask clip for hijab, using 3D printing. The clips were tested in a local hospital. The results show that the clips are very effective and easy to use. Keywords: Covid-19; Personal protective equipment; Pandemic; Movement Control Order; 3D Face mask
Research Interests:
A Mobile Augmented Reality indoor navigation framework composed of several modules to reduce human cognitive workload and save time by blending the digital and physical worlds seamlessly through aligning the appropriate 3D path with... more
A Mobile Augmented Reality indoor navigation framework composed of several modules to reduce human cognitive workload and save time by blending the digital and physical worlds seamlessly through aligning the appropriate 3D path with features in the real world through ground detection. The framework helps in better understanding the surrounding especially unfamiliar buildings such as offices, shopping malls and libraries etc. It determines the users starting location via scanning the reference image which is placed at the entrance. The system was tested at the Centre for Academic Information Services (CAIS), Universiti Malaysia Sarawak (UNIMAS). The results proved that the system provides a good platform to show the location information without requiring hardware installation and a strong wireless connection.
Research Interests:
Research Interests:
Research Interests:
Pandemics are highly unlikely events, therefore, we need a system to understand the statistics about the pandamic. Machine learning algorithms can analyse the data and then we can plan for handling the pandamic. To date, many people are... more
Pandemics are highly unlikely events, therefore, we need a system to understand the statistics about the pandamic. Machine learning algorithms can analyse the data and then we can plan for handling the pandamic. To date, many people are suffering because of the lack of reliable information system. The problem is that there is no integrated system to use the data and plan for pandemic management to minimise social panic. This study aims to provide a system, using COVID-19 data as a sample to visualise and analyse cases, deaths, discharged ICU cases updates in Malaysia as a whole state wise of COVID-19 daily statistics. The results provide visualisation and case comparison among states in Malaysia to easily and quickly understand the situation. This will help and assist the management in decision-making.
Research Interests:
Research Interests:
Smartphone usage has revolutionized the world to many settings including that of the education system with numerous potential and realized benefits. While the functions of smartphones, such as text messaging, multimedia, and Internet... more
Smartphone usage has revolutionized the world to many settings including that of the education system with numerous potential and realized benefits. While the functions of smartphones, such as text messaging, multimedia, and Internet connectivity, may seem purely recreational, they can be used within the academic institution to manage students attendance to speed up the process of taking attendance by academic instructors, hence reduces time, human errors and redundant works as compared to the manual attendance system. In this paper, we introduced an automatic examination attendance system on smartphones based on the Barcode to automatically capture student examination attendance. Although many existing systems (Sudha et al. 2015) have been proposed using smartphones for automatic student attendance, there is little study known about a system that is specifically designed for capturing student examination attendance. The main difference among our system and existing systems is that ...
Research Interests:
The deaf-mutes population always feels helpless when they are not understood by others and vice versa. This is a big humanitarian problem and needs localised solution. To solve this problem, this study implements a convolutional neural... more
The deaf-mutes population always feels helpless when they are not understood by others and vice versa. This is a big humanitarian problem and needs localised solution. To solve this problem, this study implements a convolutional neural network (CNN), convolutional-based attention module (CBAM) to recognise Malaysian Sign Language (MSL) from images. Two different experiments were conducted for MSL signs, using CBAM-2DResNet (2-Dimensional Residual Network) implementing “Within Blocks” and “Before Classifier” methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time are recorded to evaluate the models' efficiency. The experimental results showed that CBAM-ResNet models achieved a good performance in MSL signs recognition tasks, with accuracy rates of over 90% through a little of variations. The CBAM-ResNet “Before Classifier” models are more efficient than “Within Blocks” CBAM-ResNet models. Thus, the best trained model o...
Research Interests:
Research Interests:
Pandemics are highly unlikely events, therefore, we need a system to understand the statistics about the pandamic. Machine learning algorithms can analyse the data and then we can plan for handling the pandamic. To date, many people are... more
Pandemics are highly unlikely events, therefore, we need a system to understand the statistics about the pandamic. Machine learning algorithms can analyse the data and then we can plan for handling the pandamic. To date, many people are suffering because of the lack of reliable information system. The problem is that there is no integrated system to use the data and plan for pandemic management to minimise social panic. This study aims to provide a system, using COVID-19 data as a sample to visualise and analyse cases, deaths, discharged ICU cases updates in Malaysia as a whole state wise of COVID-19 daily statistics. The results provide visualisation and case comparison among states in Malaysia to easily and quickly understand the situation. This will help and assist the management in decision-making.
Research Interests:
Handwriting development begins as early as infancy when children are first able to grasp a writing object and leave a mark on the paper. Handwriting is linked with brain functioning; experts suggest that handwriting skill lightens a... more
Handwriting development begins as early as infancy when children are first able to grasp a writing object and leave a mark on the paper. Handwriting is linked with brain functioning; experts suggest that handwriting skill lightens a student's cognitive load. With consistent handwriting practice, it becomes less demanding and more automatic, enabling students critical thinking and thought organization. The lack of writing skill decreases kids' capacity to carry out higher-order skills. Most of the writing intervention approaches are not multisensory and some are using substances that may be dangerous for kids such as sand or shaving cream or pipe cleaners or play-doh etc. These issues become more challenging for kids with a learning disability such as dyslexia. This empirical gap in the multisensory writing system is the target of this research. A multisensory mobile application (Wridy) is designed and developed to support kids with learning disabilities. Wridy is an early-stage multisensory writing intervention tool. It uses a dyslexia-friendly user interface, fonts and colour. Wridy is demonstrated to the teachers of the Dyslexia Association Kuching, Malaysia. The results of the survey show that Wridy is helpful and useful in learning writing alphabets especially for kids with learning disabilities such as dyslexia.
Research Interests:
Pandemics are highly unlikely events, therefore, we need a system to understand the statistics about the pandamic. Machine learning algorithms can analyse the data and then we can plan for handling the pandamic. To date, many people are... more
Pandemics are highly unlikely events, therefore, we need a system to understand the statistics about the pandamic. Machine learning algorithms can analyse the data and then we can plan for handling the pandamic. To date, many people are suffering because of the lack of reliable information system. The problem is that there is no integrated system to use the data and plan for pandemic management to minimise social panic. This study aims to provide a system, using COVID-19 data as a sample to visualise and analyse cases, deaths, discharged ICU cases updates in Malaysia as a whole state wise of COVID-19 daily statistics. The results provide visualisation and case comparison among states in Malaysia to easily and quickly understand the situation. This will help and assist the management in decision-making.
Research Interests:
A Mobile Augmented Reality indoor navigation framework composed of several modules to reduce human cognitive workload and save time by blending the digital and physical worlds seamlessly through aligning the appropriate 3D path with... more
A Mobile Augmented Reality indoor navigation framework composed of several modules to reduce human cognitive workload and save time by blending the digital and physical worlds seamlessly through aligning the appropriate 3D path with features in the real world through ground detection. The framework helps in better understanding the surrounding especially unfamiliar buildings such as offices, shopping malls and libraries etc. It determines the users starting location via scanning the reference image which is placed at the entrance. The system was tested at the Centre for Academic Information Services (CAIS), Universiti Malaysia Sarawak (UNIMAS). The results proved that the system provides a good platform to show the location information without requiring hardware installation and a strong wireless connection.
Research Interests:
A Mobile Augmented Reality indoor navigation framework composed of several modules to reduce human cognitive workload and save time by blending the digital and physical worlds seamlessly through aligning the appropriate 3D path with... more
A Mobile Augmented Reality indoor navigation framework composed of several modules to reduce human cognitive workload and save time by blending the digital and physical worlds seamlessly through aligning the appropriate 3D path with features in the real world through ground detection. The framework helps in better understanding the surrounding especially unfamiliar buildings such as offices, shopping malls and libraries etc. It determines the users starting location via scanning the reference image which is placed at the entrance. The system was tested at the Centre for Academic Information Services (CAIS), Universiti Malaysia Sarawak (UNIMAS). The results proved that the system provides a good platform to show the location information without requiring hardware installation and a strong wireless connection.
Research Interests:
Research Interests:
Augmented reality (AR) presents a particularly powerful user interface (UI) to context-aware computing environments. AR systems integrate virtual information into a person's physical environment so that he or she can get the latest... more
Augmented reality (AR) presents a particularly powerful user interface (UI) to context-aware computing environments. AR systems integrate virtual information into a person's physical environment so that he or she can get the latest information about the environment. In a limited mobile platform we propose a framework for outdoor augmented reality which covers the main problems of limited resources in mobile, such as server dependency for data management or processing and network latency.
Research Interests:
The real world objects can be recognized by using marker based and marker-less augmented reality systems. Mostly, the previous developers used markers based augmented reality systems. However, those systems actually hide the reality and... more
The real world objects can be recognized by using marker based and marker-less augmented reality systems. Mostly, the previous developers used markers based augmented reality systems. However, those systems actually hide the reality and it was also difficult to keep the markers everywhere. Furthermore, the previous marker-less approaches use client-server architecture, which is drastically affected by network latency. Smartphone camera is matured enough that it can recognize real world objects without markers. It can guide users about their location and the direction in a convenient way. The use of Smartphone is best suited for outdoor mobile augmented-reality applications. Therefore, a marker-less natural features based tracking system in mobile augmented reality was formulated. In the adapted framework, the state-of-the-art algorithm (speed up robust features) was modified for computing image features from live mobile camera image and compares with locally stored images features for recognition. Moreover, the local static database of location tagged image features using SQLite was implemented to bypass the server. The proposed system was tested in a mobile AR-prototype application using iPhone called UNIMAS Guide. It was found from the results that the adapted marker-less system could recognize the real world objects in speedy, easy and convenient way. This technology can be applied in tourism industry, surgery and educational fields.
Research Interests:
Real world objects are recognized by tracking less and tracking based techniques. Mobile augmented reality browsers are tracking less systems, which acquires location data using global positioning system and provide information in the... more
Real world objects are recognized by tracking less and tracking based techniques. Mobile augmented reality browsers are tracking less systems, which acquires location data using global positioning system and provide information in the form of maps or web links. Tracking based techniques recognize objects through markers or directly real world objects without markers. Marker based systems actually track the markers not the real objects and therefore, these approaches hides the reality. Marker-less (direct real object tracking) systems use client-server architecture. However, these are affected by network latency. The Smartphone is capable to recognize and track real world objects without any server and marker. It can guide the users about their location and also provide information in a convenient way. Therefore, an improved algorithm for tracking real world objects through natural features was formulated. The modified version of speed up robust features (SURF) was used for features f f extraction from live mobile camera image and recognition. The pose matrix from extracted features was calculated by Homography. The adapted algorithm was tested in a mobile AR-prototype application using iPhone. It was found from the results that the formulated algorithm recognized and tracked the real world objects from natural features in speedy, easy and convenient way
Research Interests:
This study presents a system for real world objects recognition and camera pose estimation from natural features in mobile augmented reality. The system recognizes real world objects in real-time directly without any marker and desktop... more
This study presents a system for real world objects recognition and camera pose estimation from natural features in mobile augmented reality. The system recognizes real world objects in real-time directly without any marker and desktop server. The system extracts natural features by using optimized "Speed up Robust Features" SURF algorithm for mobile architecture. The features are further used by pose estimation algorithm for tracking. This system will provide instant information to smart phone user about real world objects like historical places and products. The experiments show that the formulated algorithms provide stable and accurate registration, robust recognition, and tracking of real world objects from natural features in a speedy, easy, and convenient way on iPhone 4S mobile phon.
Research Interests:
Research Interests:
Stemmer is a language processing tool that has been widely used in many artificial intelligence applications for removing affixes in a word such as prefixes, infixes, and suffixes to generate the root word. This study designs an algorithm... more
Stemmer is a language processing tool that has been widely used in many artificial intelligence applications for removing affixes in a word such as prefixes, infixes, and suffixes to generate the root word. This study designs an algorithm and develops a Malay language stemmer. It is given that most of Malay language stemmers have problems in stemming, as they tended to have dependencies on online dictionaries, which return false results during stemming. It is given that the complexity of affixes in Malay words is higher than that of English words. Therefore, an offline dictionary of 9,512 words is introduced in this study to handle the ambiguity when stemming Malay words. Each step the algorithm first checks the word in the local dictionary as a root word, otherwise process the word. The five steps are stem-extra-suffix, stem-plural, stem-infix, stem-prefix, and stem-suffix. The affixes rules are extracted from Kamus Tatabahasa, and Kamus Dewan (4th Ed) is used to confirm the accuracy of stemmed words. The results show that the proposed stemmer can stem prefixes, suffixes and infixes with high accuracy. The study conclusively illustrated that the proposed stemmer can handle the complexity of Malay words. This stemmer can be further enhanced by a look-up table or dictionary of overlapping words to cover the prefix and suffix overlapping limitation.
Research Interests:
New generation is the future of every nation, but dyslexia which is a learning disability is spoiling the new generation. Most experts are using manual techniques to diagnose dyslexia. Machine learning algorithms are capable enough to... more
New generation is the future of every nation, but dyslexia which is a learning disability is spoiling the new generation. Most experts are using manual techniques to diagnose dyslexia. Machine learning algorithms are capable enough to learn the knowledge of experts and intelligently diagnose and classify dyslexics. This research proposes such a machine learning based diagnostic and classifica tion system. The system is trained by human expert classified data of 857 school children scores in various tests. The data was collected in another fundamental research of designing special tests for dyslexics. Twenty-fifth percentile was used as threshold. The scores equal to the threshold and below were marked as indicators of children who were likely to have dyslexia while the scores above the threshold were considered to be indicators of children who were non-dyslexic. The system has three components: the diagnostic module is a pre-screening application that can be used by experts, trained users and parents for detecting the symptoms of dyslexia. The second module is classification, which classifies the kids into two groups, non-dyslexics and suspicious for dyslexia. A third module is an analysis tool for researchers. The results show that 20.7% of students seem to be dyslexic out of 257 in the testing data set which has confirmed by human expert.
Research Interests:
Smartphone usage has revolutionized the world to many settings including that of the education system with numerous potential and realized benefits. While the functions of smartphones, such as text messaging, multimedia, and Internet... more
Smartphone usage has revolutionized the world to many settings including that of the education system with numerous potential and realized benefits. While the functions of smartphones, such as text messaging, multimedia, and Internet connectivity, may seem purely recreational, they can be used within the academic institution to manage students attendance to speed up the process of taking attendance by academic instructors, hence reduces time, human errors and redundant works as compared to the manual attendance system. In this paper, we introduced an automatic examination attendance system on smartphones based on the Barcode to automatically capture student examination attendance. Although many existing systems (Sudha et al. 2015) have been proposed using smartphones for automatic student attendance, there is little study known about a system that is specifically designed for capturing student examination attendance. The main difference among our system and existing systems is that existing systems are using extra hardware device Barcode reader while our system is using smartphone, which highly reduce the cost. Our experiment shows that our proposed student examination attendance system is better for capturing the student attendance information during the examination as compared to the general student attendance systems.
Research Interests:
Children with dyslexia have difficulties with accurate word recognition, poor spelling and inability to differentiate certain phoneme and colours. Writing is another issue that is faced by most kids with dyslexia. There are many font... more
Children with dyslexia have difficulties with accurate word recognition, poor spelling and inability to differentiate certain phoneme and colours. Writing is another issue that is faced by most kids with dyslexia. There are many font families, text colour contrast and input methods for interface designing such as word selection, dropdown list and typing from a keyboard. There is a need to investigate, what font family, input method, and colour can ease children with dyslexia. Therefore, this study aims to explore and propose a suitable font, colour and input method for children with dyslexia. For this purpose, we have designed a mobile application having several user interfaces to test with a group of children with dyslexia. Comparison results was further concluded to be a set of recommendations for future interface design for them.