Shuzlina Abdul Rahman

Universiti Teknologi MARA | UiTM · Faculty of Computer and Mathematical Sciences

User-generated content is critical for tourism destination management as it could help them identify their customers' opinions and come up with solutions to upgrade their tourism organizations as it could help them identify customer opinions. There are many reviews on social media and it is difficult for these organizations to analyse the reviews m...

This study investigates the suitable model for flower recognition based on deep Convolutional Neural Networks (CNN) with transfer learning approach. The dataset used in the study is a benchmark dataset from Kaggle. The performance of CNN for plant identification using images of flower are investigated using two popular image classification models:...

Plants are essential in the Earth, as it supplies the oxygen needed by human beings and animals, and becomes the source of foods and medical treatments. Many medicinal plants can treat diseases and it is also called herbal plants. Traditionally, these plants are processed and transformed as traditional medicines to cure any diseases. Nowadays, ther...

Livestream videos are becoming the norm in this digital era. With the advancement of streaming technology, real-time sharing has been effortless for many of the global population. There are many platforms that allow anyone to create or view livestream videos. This situation, however, creates a high possibility of showing inappropriate videos as wel...

Customer segmentation is important because it can help businesses to reach out to all of the customers in the market. Without customer segmentation, it is difficult to develop a marketing strategy that fits for all groups of people. Many research papers exploit the general attributes in finding the customer segmentation. However, there are several...

House price is affected significantly by several factors and determining a reasonable house price involves a calculative process. This paper proposes advanced machine learning (ML) approaches for house price prediction. Two recent advanced ML algorithms, namely LightGBM and XGBoost were compared with two traditional approaches: multiple regression...

Internet penetration in the majority of Indonesian cities has exponentially increased, as seen from the increasing number of internet users in schools, businesses and society in general. The purpose of internet use varies to include searching for information, sending emails, chatting, entertainment, as well as buying and selling goods/services, amo...

Customer segmentation and profiling has become an important marketing strategy in most businesses as a preparation for better customer services as well as enhancing customer relationship management. This study presents the segmentation and classification technique for insurance industry via data mining approaches: K-Modes Clustering and Decision Tr...

This systematic review article focuses on the factors that lead to consumer behavior in online shopping. Online shopping is generally a popular shopping platform for consumers. Consumer behavior in online shopping is different from the retail market where he/she has access to an item on online shopping sites that is quickly replacing traditional or...

This paper explores the capabilities of a graph optimization-based Simultaneous Localization and Mapping (SLAM) algorithm known as Cartographer in a simulated environment. SLAM refers to the problem in which an agent attempts to determine its location in the immediate environment as well as constructing the map(s) of its environment. SLAM is one of...

This paper presents visual analytics of 3D LiDAR point clouds in robotics operating system. In this study, experiment on Simultaneous Localization and Mapping (SLAM) using point cloud data derived from the Light Detection and Ranging (LiDAR) technology is conducted. We argue that one of the weaknesses of the SLAM algorithm is in the localization pr...

Predictive analytics extract important factors and patterns from historical data to predict future outcomes. This paper presents predictive analytics of university student intake using supervised methods. Every year, universities face a lot of academic offer rejection by the applicants. Hence, this research aims to predict student acceptance and re...

This paper presents a heuristic based model for groceries shopping navigator that attempts to improve the navigation problem that usually face by customers while doing their shopping. A system known as Shopping Navigator or shortly SHoNa was developed to give the optimal sequence of shelves to be visited by the customer and the total estimated shop...

span>Abstract—This paper presents a simulation study of Simultaneous Localization and Mapping (SLAM) using 3D point cloud data from Light Detection and Ranging (LiDAR) technology. Methods like simulation is useful to simplify the process of learning algorithms particularly when collecting and annotating large volumes of real data is impractical and...

This study focuses on the use of machine learning algorithms to analyse financial news on stock market prices. Stock market prediction is a challenging task because the market is known to be very volatile and dynamic. Investors face these kinds of problems as they do not properly understand which stock product to subscribe or when to sell the produ...

Student attrition in higher educational institutions (HEI) concern with the failure of undergraduate students who unable to complete their studies within the stipulated period. Student attrition problem relates to the resource’s usage in which dropout students still use the same resources as graduated students though they do not yield any outcomes....

Logistic regression is one of the classical methods for classification. Meanwhile, neural network is the recent method for classification. Both methods are widely used in the supervised learning and competing to be the best methods in many classifications research. This paper aims to study the performance of both methods using data of youth interne...

Online medium has become popular among knowledgeable society as a new emerging platform of information gathering and sharing where their thoughts and opinions are considered important in many aspects of nation building. The overwhelmed of online opinionated data has created a great challenge for researchers to mine sentiments accurately. Sentiment...

In most universities, the number of students who graduated on time reflect tremendously on their operation costs. In such cases, the high number of graduate-on-time or GOT students achievement will indirectly reduce the university’s annual operation cost per student. Not as trivial as it seems, to ensure most of the students able to GOT is challeng...

Radio Frequency Identification (RFID) is a one of the fastest growing and most beneficial technologies being adopted by businesses today. One of the important issues is localization of items in a warehouse or business premise and to keep track of the said items, it requires devices which are costly to deploy. This is because many readers need to be...

This paper is an investigation about the MNIST dataset, which is a subset of the NIST data pool. The MNIST dataset contains handwritten digit images that is derived from a larger collection of NIST data which contains handwritten digits. All the images are formatted in 28 × 28 pixels value with grayscale format. MNIST is a handwritten digit images...

There are many factors that influence classifiers behavior in machine learning, and thus determining the best classifier is not an easy task. One way of tackling this problem is by experimenting the classifiers with several performance measures. In this paper, the behaviors of machine learning classifiers are experimented using the Rattle tool. Rat...

Social networks play an important role in commercial products, and thus knowing the emotions and opinions of users is very useful in improving services, sales, business and marketing strategies. This paper illustrates the text mining and sentiment analysis approach to gain valuable insights into consumer perceptions towards Proton cars in Malaysia....

Sentences are the language of human communication. This communication medium is so fluid that words and meaning can have many interpretations by readers. Besides, a document that consists of thousands of sentences would be tough for the reader to understand the content. In this case, computer power is required to analyse the gigantic batch size of...

The overall purpose of this paper is to provide an introductory survey in the area of Simultaneous Localization and Mapping (SLAM) particularly its utilization in autonomous vehicle or more specifically in self-driving cars, especially after the release of commercial semi-autonomous car like the Tesla vehicles as well as the Google Waymo vehicle. B...

Online opinionated data has increased tremendously since the arrival of web 2.0. Users have the authority to generate online content expressing their sentiments or opinions regarding subjects of interest. Although these phenomena caused the problem of information overload, the opinionated data is valuable and beneficial to others. Looking at the pr...

A lot of algorithms performing Frequent Itemsets Mining (FIM), however, some of the glitches in the algorithms still require attention, particularly when the mining process involves a high dimensional dataset. The Directed Acyclic Graph in High Dimensional Dataset Mining (DAGHDDM) is a graph-based mining algorithm that represents itemsets in the co...

Genome wide association study (GWAS) is a study to investigate the correlations between genetic variants and traits. GWAS normally focus on the associations between single-nucleotide polymorphisms (SNPs) and traits like major human diseases. Generally, GWAS uses standard statistical tests on each SNP to capture main the genetic effects. However, th...

Social media sites are websites used as mediums to create and share various types of contents over the internet. These sites can also be accessed through applications on mobile gadgets. Different social media sites are available for free, and most teenagers or youths have at least one active account. They use social media sites to connect and share...

Paddy weed appears to be one of the many visible threats to paddy crop production and subsequently farmers’ income. It is for this reason that the growth of paddy weeds in paddy fields should be controlled as it results in a significant decrease of paddy yields. However, farmers might have limited knowledge on weed types, and are thus unable to ide...

Feature selection has been widely applied in many areas such as classification of spam emails, cancer cells, fraudulent claims, credit risk, text categorisation and DNA microarray analysis. Classification involves building predictive models to predict the target variable based on several input variables (features). This study compares filter and wr...

This study focuses on the use of machine learning algorithms to construct a model that can predict the movements of Bursa Malaysia stock prices. In this research, we concentrate on linguistics terms from financial news that can contribute movements of the prices. Our aim is to develop a prototype that can classify sentiments towards financial news...

There are many factors and ways to increase the quality and quantity of paddy yields. One of the factors that can affect the quality of paddy is the amount of fertilizer used. The optimum amount of fertilizer for any field in any year cannot be determined with absolute certainty, thus in this project, we aim to find the optimum amount of nitrogen f...

Agriculture industry is one of the main economic activities in Asean countries. The activities involved a lot of crop planting and yield production in paddy, rubber, oil palm and so forth. Meanwhile in Malaysia, paddy is the third most widely planted crop after oil palm and rubber. Rice, produced by paddy, is considered to be one of Malaysia and As...

Most research concluded that machine learning performance is better when dealing with cleaned dataset compared to dirty dataset. In this paper, we experimented three weak or base machine learning classifiers: Decision Table, Naive Bayes and k-Nearest Neighbor to see their performance on real-world, noisy and messy clinical trial dataset rather than...

This paper describes the performance of a shallow network towards increasing complexity of dimension in an image input representation. This paper will highlight the generalization problem in Shallow Neural Network despite its extensive usage. In this experiment, a backpropagation algorithm is chosen to test the network as it is widely used in many...

Nowadays, there are a number of algorithms that have been proposed in frequent itemsets mining (FIM). Data projection is one of the key features in FIM that affects the overall performance. The aim is to speed up the searching process by rearranging the items in a more compact form and to fit all the items in the data set in main memory efficiently...

The performance of feature selection method is typically measured based on the accuracy and the number of selected features. The use of particle swarm optimization (PSO) as the feature selection method was found to be competitive than its optimization counterpart. However, the standard PSO algorithm suffers from premature convergence, a condition w...

The advancement of web technologies has changed the way people share and express their opinions. People enthusiastically shared their thoughts and opinions via online media such as forums, blogs and social networks. The overwhelmed of online opinionated data have gained much attention by researchers especially in the field of text mining and natura...

Data mining consists of crucial tasks in discovering knowledge and hidden patterns and the tasks are significant in the various areas, such as marketing, biomedical, drugs design, event sequences and etc. Frequent pattern mining is a method that has been explored by a lot of researches in discovering new or hidden knowledge. Therefore, this researc...

Nowadays, there are abundant of big data collection and to understand its patterns would need a thorough analysis. Analyzing big data would depend highly on the purpose and the tasks involved would be various. One of the significant tasks is frequent itemsets mining and the strategy has been evolved in many ways in order to improve the efficiency a...

Huge volume of online content in the era of web 2.0 increases difficulties in seeking information. Users are unable to get the right information based on their needs and preferences. Information filtering is capable to overcome the problems of information overload by filtering irrelevant information. There has been much work done in this area to in...

This paper describes the application of swarm algorithms on bioinformatics data namely protein sequences. The big data that exists in bioinformatics domains require an intelligent method that capable to increase the performance of classification as well as discovering the knowledge. The work optimizes the big features that exist in protein sequence...

With the growing number of text documents in the Internet, it is difficult for users to search, find, manage and organize information quickly. Normally, text documents are classified manually and it is time-consuming. Text categorization is a process of assigning text documents into a set of fixed predefined categories. The high dimensionality of t...

Frequent pattern mining (FPM) is a popular method in discovering knowledge through generating associations between the attributes in database. Frequent patterns (FPs) represent interesting relationship that could improve understanding the data. High throughput genomic datasets normally consists of a lot of hidden relationships that can be discovere...

The employment of feature selection algorithms (FSAs) prior to classification has become a necessity due to an enormous growth of public sequence databases and the nature of high dimensionality in protein sequences. This paper provides a comparative framework on four multivariate FSAs for finding minimal feature subsets prior to classification of a...

Current development in biological sciences and data sharing have contributed a lot of advantages by increasing the number of research in computer sciences. These researches could manipulate environmental and genetic factors that influence and increase the risk to diseases. Genome wide association studies (GWAS) are the studies that exploit genetic...

Dermatology or skin disease is one of the popular diseases among other diseases these days. The features similarities between different types of skin diseases make diagnosis of skin diseases very complex. A patient needs dermatologist that has a sound and vast good experience in skin diseases in order to give precise results at the right time. This...

Most of the health care companies have shown their efforts in putting their patients' record properly. The patients' record would be very useful in discovering knowledge and identifying patterns, such as for disease detection. In order to exercise pattern identification task, we chose medical dataset from UCI as our preliminary study. We focused ou...

With the availability of biological data and the power of sharing, it produces many opportunities for computer scientists to perform researches in bioinformatics. Generally the researches propose methods for different tasks, mainly to develop algorithms in diagnosing and identification of diseases. One of the primary studies that relevant to health...

Turf grass needs water to survive and stay green, but too much water can really damage it. Turf grass irrigation processes can lead to excess water consumption. The irrigation process is based on several factors, which are evapotranspiration rate, grass evapotranspiration rate and tensiometer reading. This study proposes an irrigation process syste...

Pre-processing plays a vital role in classification tasks, particularly when complex features are involved, and this demands a highly intelligent method. In bioinformatics, where datasets are categorised as having complex features, the need for pre-processing is unavoidable. In this paper, we propose a framework for selecting the discriminatory fea...

This paper attempts to predict the survival of patients using supervised machine learning techniques. To predict this task, the variables were identified and retrieved from the StatLib database. Both the artificial neural networks and linear regression models were used to perform the task. Experimental results, based on the classification accuracy...

Particle Swarm Optimisation (PSO) algorithm is known to be better than Genetic Algorithm (GA) as fewer operators are needed in its algorithm. However, it still has some weaknesses such as immature convergence; a condition whereby PSO tends to get trapped in a local optimum. This condition prevents them from being converged towards a better position...

Signature is a popular method of seeking approval and authentication between various parties in many transaction applications. Signature pattern recognition is done by processing a set of data that consists of (x, y) coordinates, representing online signature. Particle Swarm Optimisation technique is used to find and analyse the baseline feature th...

Signature is a typical method in authenticating identities. It is commonly used in many official transactions as a symbol of approval and agreement between all parties involved in the specified transactions. Although many individuals can possess the same name in their birth certificates, their signature still differs from one person to another. The...

Protein features are often complex, and they are challenging to classify. In identifying the most discriminatory features in protein sequences, we propose a new feature-selection strategy by integrating the multivariate filter and Particle Swarm Optimisation (PSO) algorithms. Experimental results, based on the number of reducts and classification a...

This paper discusses the application of two unsupervised methods in classifying type of soils. Soils that are suitable for agricultural activities can be classified into four classes which are hill soil, organic soil, alteration soil and alluvium soil. In addition, no specific support system is able to classify the type of soil and retrieve the inf...

This paper proposes a new feature-selection strategy by integrating the Rough Set Theory (RST) and Particle Swarm Optimisation (PSO) algorithms to generate a set of discriminatory features for the classification problem. The proposed method is seen as a marriage between filter and wrapper approaches in which the RST is used to pre-reduce the featur...

There are various methods in data mining that can be applied in classification data. This paper discusses the experiments done in classifying ICU data. The dataset consists of 25 variables for 410 patients. The goal of this experiment is to determine the survival of the patients, so the targeted output are alive and dead. Three selected data mining...

This paper proposed a feature selection strategy based on rough set theory (RST) and discrete particle swarm optimization (DPSO) methods prior to classify protein function. RST is adopted in the first phase with the aim to eliminate the insignificant features and prepared the reduce features to the next phase. In the second phase, the reduced featu...

Machine learning methods are known to be inefficient when faced with many features that are unnecessary for rule discovery. In coping with this issue, many methods have been proposed for selecting important features. Among them is feature selection that selects a subset of discriminative features or attribute for model building due to its ability t...

A vector rule-based approach and analysis to on-line slant signature recognition algorithm is presented. Extracting features in signature is an intense area due to complex human behavior, which is developed through repetition. Features such as direction, slant, baseline, pressure, speed and numbers of pen ups and downs are some of the dynamic infor...

Signature verification and recognition can be divided into online and offline, depending on the sensing modality. In an online method, the dynamic information signature features such as direction, slant, baseline, pressure, speed and numbers of pen ups and downs can be captured. Method of extracting features signature depends on the requirement fea...