Rosalina Abdul Salam

USIM | Universiti Sains Islam Malaysia | usim · Faculty of Science and Technology

This paper presents a Dynamic Gradient Pattern (DGP) based on Kalman filtering technique for urban road users tracking. DGP technique is proposed to enhance rigid object descriptive ability for improved verification. DGP descriptor along with weighted centroid was integrated with a Kalman filtering framework to enhance data association robustness a...

Automatic vehicle detection in urban traffic surveillance is an important and urgent issue, since it provides necessary information for further processing. Conventional techniques utilize either motion segmentation or appearance-based detection, which involves either poor adaptation or high computation. The complexity of urban traffic scenarios lie...

Hadith refers to the speeches, actions, tacit approval and characteristics of Prophet Muhammad PBUH. It contains many aspects of Islam and life such as creed, ibadah, ethics and others. Ibadah (Act of Worship) is pivotal for Muslims as it depicts the ritual of devotion to Allah. The word samica which defines hearing is well-known in the world of ha...

Accurate and precise vehicle recognition and classification play a major role in analyzing and understanding traffic surveillance systems. This paper proposes a dynamic feature descriptor to recognize and classify road users based on graph representation. Local gradient patterns are computed based on the grayscale difference on the four directions...

The Holy Quran ontology models are gaining popularity among researchers due to people's demands in understanding this divine book. Due to this, there are many studies and research have been conducted in this area to facilitate people's understanding of the Quran. The Quran knowledge is represented conforming to an ontology within a system framework...

Al-Quran is the most recited holy book in the Arabic language. Over 1.3-billion Muslim all over the world have an obligation to recite and learn Al-Quran. Learners from non-Arabic as well as from Arabic speaking communities face difficulties with Al-Quran recitation in the absence of a teacher (ustad) around. Advancement in speech recognition techn...

Vehicle detection is a fundamental step in urban traffic surveillance systems, since it provides necessary information for further processing. Conventionaltechniques utilize either background subtraction orforeground appearance-baseddetection, which involves either poor adaptation or high computation. The complexity of urban traffic scenarios lies...

The haze phenomenon exerts a degrading effect that decreases contrast and causes colour shifts in outdoor images. The presence of haze in digital images is bothersome, unpleasant, and, occasionally, even dangerous. The atmospheric light scattering (ALS) model is widely used to restore hazy images. In this model, two unknown parameters should be est...

The impact of rain streaks on single images can make it difficult to recognize the surrounding environment using an outdoor camera. Furthermore, a single image is important to use in numerous areas such as in object recognition and scientific research. Therefore, outdoor images and videos in rainy weather conditions will reduce visibility, and dama...

Sahih al-Bukhari is considered as the most authentic book of hadith. One of the important aspects in the hadith study is the hadith understanding. Contextual approach is one of the approaches in the hadith understanding. The Islamic scholars have written several books of commentaries in order to explain the hadith content based on its context. Howe...

The Holy Quran being the most comprehensive book of reference has discussed on every minute details of human anatomy. One of them is human senses and can be categorized by external parts and internal parts. For example external parts such as ears are used to sense audio, eyes are used to sense visual, and nose is used to sense smell. While for inte...

Hadith which defined as the speeches, actions, tacit approvals and characteristics of Prophet Muhammad PBUH requires thorough attention in understanding. One of the principles in comprehending hadith is by understanding the content contextually, and it could be done by gathering related hadith under a certain concept. Ontology could play the role i...

Segala bentuk percakapan, perbuatan, pengakuan, sikap serta sifat fizikal Rasulullah SAW dirakamkan di dalam hadis. Baginda SAW merupakan contoh terbaik kepada sekalian umat manusia.Terdapat banyak kajian berkaitan hadis yang mengupas tentang keistimewaan baginda SAW ini, namun ia masih bersifat umum dan tidak mengaitkannya dengan jenis hadis mahup...

Motion segmentation is a fundamental step for vehicle detection especially in urban traffic surveillance systems. Temporal frame differencing is the simplest and fastest technique that is used to identify foreground moving vehicles from static background scene. Conventional techniques utilize background modelling and subtraction, which involves poo...

There seems to be lack of academic papers trying to set out a concept of sama' (hearing) verses ontology. Hence this study wishes to fill in the gap by describing a new concept of Quran ontology for the sama' verses from an existing data. This study also aims to highlight the unique features of sama' verses by using data extraction based on ontolog...

Video-based analysis of traffic surveillance is an active area of research, which has a wide variety of applications in intelligent transport systems (ITSs). In particular, urban environments are more challenging than highways due to camera placement, background clutter, and vehicle pose or orientation variations. This paper provide a comprehensive...

Motion segmentation is a fundamental step in urban traffic surveillance systems, since it provides necessary information for further processing. Background subtraction techniques are widely used to identify foreground moving vehicles from static background scene. Conventional techniques utilize single background model or Gaussian mixture model, whi...

Outdoor images that are captured in bad weather conditions have low contrast and infidelity colours. Under the turbid medium conditions such as haze, mist, fog and drizzle, the light which reaches to the sensor is attenuated by atmospheric particles. These atmospheric phenomena degrade the contrast intensity of outdoor images based on haze density....

Allah has various names depicting His attributes. al-Samī c has been recognized as one of the beautiful names of Allah (Asmaul Husna) and Sami c a is the root word of al-Samī c. Sami c a means to hear. Hearing of Allah and his beings differ in certain aspects. Numerous repetitions of word Sami c a exist in al-Quran and Hadith. Previous research has...

Abstrak Asmaul Husna merupakan kumpulan 99 nama-nama Allah. Kesemua nama yang bernaung di bawah Asmaul Husna merupakan nama yang mempunyai keindahan dan kebaikan bertepatan dengan sifat Allah yang Maha Sempurna. Kebanyakan kajian-kajian terdahulu yang berkaitan dengan Asmaul Husna lebih fokus perbahasannya kepada konteks Al-Quran. Justeru, kajian t...

Outdoor machine vision is getting a concern nowadays. Ranging from surveillance and monitoring system to automotive system such as driver assistance system require vision application or artificial eye to keep monitoring the situations. However, most of these applications works very well during clear weather and degrade during bad weather due to the...

Requirements engineering (RE) is an integral and fundamental part of software development life cycle (SDLC). The most cited reason for software failure is the inability to fully capture and implement the exact user requirements in a timely, operationally and financially expected manner. Requirements can be categorized into two types; explicit and t...

Clustering is one of the most common automated segmentation techniques used in the fields of bioinformatics applications specifically for the microscopic image processing usage. Recently many scientists have performed tremendous research in helping the haematologists in the issue of segmenting the leukocytes region from the blood cells microscopic...

Rain, fog and haze are natural phenomena that fade scenes, limit the visibility range, and cause shifts in colors. These phenomena also play a decisive role in determining the degree of reliability of many kinds of outdoor applications, such as aerial and satellite imaging, surveillance, and driver assistance systems. Thus, removing their effects f...

Clustering is one of the most common automated image segmentation techniques used in many fields including machine learning, pattern recognition, image processing, and bioinformatics. Recently many scientists have performed tremendous research in helping the hematologists in the issue of segmenting the blood cells in the early of prognosis. This pa...

The visibility of a scene is degraded by weather phenomena such as rain drizzle, fog and haze. The degradation of image scene is due the substantial presence of particles in the atmosphere that scatter and absorb light. As the light spreads from object to the observer, the color and intensity is changed by the atmospheric particles. In this researc...

Image segmentation is an important phase in image recognition system.In medical imaging such as blood cell analysis, it becomes a crucial step in quantitative cytophotometry. Currently, blood cell images become predominantly valuable in medical diagnostics tools.In this paper, we present a comparative analysis on several segmentation algorithms. Th...

Bad weather conditions lead the robustness of most surveillance and driver assistance system. Therefore this paper attempts to review the type of bad weather in a perspective of computer vision and image processing and some recent effort on raindrop detection and removal techniques which has been successfully designed and developed to enhance the i...

In blood cell image analysis, segmentation is crucial step in quantitative cytophotometry. Blood cell images have become particularly useful in medical diagnostics tools for cases involving blood. In this paper, we present a better approach on merging segmentation algorithms of K-means and Median-cut for colour blood cells images. Median-cut techni...

Many factors, such as noise level in the original image and the noise-removal methods that clean the image prior to performing a vectorization, may play an important role in affecting the line detection of raster-to-vector conversion methods. In this paper, we propose an empirical performance evaluation methodology that is coupled with a robust sta...

Underwater images are affected by reduced contrast and non-uniform colour cast due to the absorption and scattering of light in the aquatic environment. This affects the quality and reliability of image processing and therefore colour correction is a necessary pre-processing stage. In this paper, we propose an Unsupervised Colour Correction Method...

Basically, detecting convex and concave points on the boundary of an object plays an important role in computer vision, object recognition and image understanding. In this paper a method that combines boundary and skeleton information for detecting these critical points is proposed. Specifically, the method is developed with the aim of obtaining hi...

In this paper an enhanced background subtraction approach for image segmentation is proposed in order to precisely detect and represent the objects in the images. It is based on automatic detection of the background by estimating the background and then subtracting it from the original image. This step is incorporated in the background subtraction...

Feed-Forward Artificial Neural Networks (FFANN) can be trained using Genetic Algorithm (GA). GA offers a stochastic global optimization technique that might suffer from two major shortcomings: slow convergence time and impractical data representation. The effect of these shortcomings is more considerable in case of larger FFANN with larger dataset....

This paper presents a novel technique for the supervised training of feed-forward artificial neural networks (ANN) using the Harmony Search (HS) algorithm. HS is a stochastic meta-heuristic that is inspired from the improvisation process of musicians. Unlike Backpropagation, HS is non-trajectory driven. By modifying an existing improved version of...

Many failures associated with software development in particular Web-based applications are due to poor awareness of risks involved and the weak management of these risks. Hence, effective risk management has become the essential factor in ensuring the success of the Web project management. We propose RIAP (Risk Identification Architecture Pattern)...

In this paper a noise removal algorithm is proposed by adding a procedure to enhance noise removal to a third party algorithm as a post processing step. The procedure (TAMD) has been proposed to enhance salt and pepper noise removal. TAMD analyzes thin line blobs before deciding to retain or remove them. It has been successfully applied previously...

Representation and description of object shapes by the slopes of their contours or borders are proposed. The idea is to capture the essence of the features that make it easier for a shape to be stored, transmitted, compared and recognized. These features must be independent of translation, rotation and scaling of the shape. A approach is proposed t...

From the software engineering point of view, the development of web applications is a new area that requires an adaptation of many software engineering approaches or even the development of completely new approaches. Many failures associated with web applications development are the consequences of poor awareness of the risks involved and the weak...

This paper presents a work in progress that aims to reduce the overall training and processing time of feed-forward multi-layer neural networks. If the network is large processing is expensive in terms of both; time and space. In this paper, we suggest a cost-effective and presumably a faster processing technique by utilizing a heterogeneous distri...

Noise removal in engineering drawing is an important operation performed before other image analysis tasks. Many algorithms have been developed to remove salt-and-pepper noise from document images. Cleaning algorithms should remove noise while keeping the real part of the image unchanged. Some algorithms have disadvantages in cleaning operation tha...

In this paper a simulated control system for robot is designed by using distributed learning classifier system to perform complex behaviors. A set of enhanced solutions of cover detectors problem is suggested and compared with each other in order to make the simulated robot more effective in choosing the appropriate behavior (action).

Risk management is an essential fraction of project management, which plays a significant role in project success. Many failures associated with Web projects are the consequences of poor awareness of the risks involved and lack of process models that can serve as a guideline for the development of Web based applications. To circumvent this problem,...

Robotic system is an important area in artificial intel-ligence that aims at developing the performance techniques of the robot and making it more efficient and more effective in choosing its correct behavior. In this paper the distributed learning classifier system is used for designing a simulated control system for robot to perform complex behav...

Image segmentation based on an adaptive K-means clustering algorithm is presented. The proposed method tries to de-velop K-means algorithm to obtain high performance and efficiency. This method proposes initialization step in K-means algorithm. In addition, it solves a model selection number by determining the number of clusters using datasets from...

Removing noise in engineering drawing images is important before applying image analysis processes. Noise should be removed while keeping the fine detail of the image intact. A noise removal algorithm that can remove noise while retaining fine graphical elements is presented in this paper. The algorithm studies the neighborhood of thin lines before...

In this paper, a hybrid of mean-shift and median-cut algorithm was introduced to perform segmentation on color images. Firstly, the image pre-processing technique was applied to enhance the image before changing the color space to LUV color space. Then mean-shift segmentation was introduced. However, some region has no semantic meaning since the me...

In this paper distributed learning classifier system is used to design a control system for robot. We suggest an enhanced approach to determine the steady state values for the strength and the bid of classifiers to call genetic algorithm (GA) that works in rule discovery system in learning classifier system (LCS) in order to improve the efficiency...

Proteins are essential for the biological processes in the human body. They can only perform their functions when they fold into their tertiary structure. Protein structure can be determined experimentally and computationally. Experimental methods are time consuming and high-priced and it is not always feasible to identify the protein structure exp...

Web projects tend to have a high possibility of loss or failure compared to traditional projects. For this reason, risk management is becoming more emphasized and systemized in Web projects so as to improve the quality of difficult decisions that normally encompass a higher level of risk exposures. Software architecture process is seen as iterative...

Artificial neural networks are widely used in diverse fields of science and industry. Though there have been numerous techniques used for their implementations, the choice of a specific implementation is subjected to different factors including cost, accuracy, processing speed and overall performance. This survey encompasses many recent well-known...

Web projects continually face a high degree of visible developmental failure. Such inefficiencies in web projects cost losses in terms of money and time thus negatively impacting on business growth. Web development projects have an array of unique risks different from those found in traditional software development projects. Many failures associate...

Proteins perform many biological functions in the human body. The structure of the protein determines its function. In order to predict the protein structure computationally, protein must be represented in a proper representation. To this end, an energy function is used to calculate its energy and a conformational search algorithm is used to search...

Bipartite graph-based matching technique has a powerful ability to give a global and optimized matching result. At the same time, we can take the advantage of graph-based data representation used with the technique. Graph-based representation has the ability to encapsulate the attribute of the objects and also the relationship details among the ele...

This paper describes a new segmentation algorithm for handwritten Arabic characters using Rotational Invariant Segments Features (RISF). The algorithm evaluates a large set of curved segments or strokes through the image of the input Arabic word or subword using a dynamic feature extraction technique then nominates a small optimal subset of cuts fo...

Cell Imagery has been widely used in a variety of applications over the past few years. In order to recognise this cell image, it has to be transformed into particular platform. Typically, cell images have to be segmented into certain parts or areas so that it can be analyse for further classification and recognition. Segmentation of images is the...

Advances in technology and the use of the Internet have had a massive and permanent influence on our lives. In this regard, there is growing concern about the type of development and the long-term quality of Web applications, which form the largest share of individual software developed today. Web applications is a new application domain that requi...

Development of robot behaviors is an important area in artificial intelligence. The goal of this development is to make the robot choose correct action with higher efficiency and accuracy .Learning classifier system (LCS) is a type of machine learning that is based on genetic algorithm (GA). Learning process in LCS is achieved by bucket brigade alg...

In this paper we study different factors that affect vector quality. Noise level, cleaning method, and vectorization software are three factors that may influence the resulting vector data. Real scanned images from GREC'03 contest are used in the experiment. Three different levels of salt-and-pepper noise (5%, 10%, and 15%) are used. Noisy images a...

Designing a simulated system and training it to optimize its tasks in simulated environment helps the designers to avoid problems that may appear when designing the system directly in real world. These problems are: time consuming, high cost, high errors percentage and low efficiency and accuracy of the system. The proposed system will investigate...

Designing a simulated system and training it to optimize its tasks in simulated environment helps the designers to avoidproblems that may appear when designing the system directly in real world. These problems are: time consuming, high cost, higit errors percentage and low efficiency and accuracy of the system. The proposed system will investigate...

Digital image processing is required for almost all type of images. Live-cell images are one of those image requires digital image processing. This paper proposed a centre weighted median filter for live-cell video enhancement. Three different types of filters were compared and results showed that the most effective filter is the centre weighted me...

In underwater situations, clarity of images are degraded by light absorption and scattering. This causes one colour to dominate the image. In order to improve the perception of underwater images, we proposed an approach based on slide stretching. The objective of this approach is twofold. Firstly, the contrast stretching of RGB algorithm is applied...

Face recognition is highly dependent on two stages that are image preprocessing and classification. Methods for feature extraction and classification have been investigated. Through the investigations a method that uses Bayesian Network for feature extraction and Backpropagation algorithm for classification has been proposed. A prototype of the sys...

Perceptrons are simple, yet effective classifiers for linearly separable problem domains. For non-linearly separable problems, back-propagation networks are typically used. However, back-propagation networks require greater effort to implement and parallelize, compared to the simple perceptron. In order to maintain simplicity, as well as the abilit...

Emotion can be expressed in ways that can be seen such as facial expression and gestures. Emotion can also be heard by detecting prosody features and other vocal characteristics. However in this research, we are interested to detect emotions from textual information. Our main objective is to predict the emotions from textual material such as e-mail...

Being a Java developer the decision of starting to use an integrated development environment (IDE) instead of a set of discrete programming tools, is to be taken sooner or later. This paper identifies the favorite features to opt for, in selecting a suitable IDE, what should be used and by whom with plethora of such IDEs. Though IDEs are meant to f...

Proteins are important and essential for biological processes and activities which are fundamental to life. Protein function is related to its structure. In order to predict the protein structure computationally, protein must be represented in suitable representation. An efficient energy function must be used to calculate the protein energy, and th...

This paper presents the combination of genetic algorithm and simulated annealing to solve multiple sequence alignment (MSA) assignment. Genetic algorithm will try to find a new region of feasible solution while simulated annealing will act as an aligning improver. There are several aspects that must be taken into consideration such as the represent...

Data Mining is used to extract the hidden information from large amount databases. Parallel/distributed computing is used which achieves scalability and improves the performance of compute intensive algorithms. A parallel version of ITL-Mine algorithm is proposed and implemented on distributed memory (shared nothing) architecture. The parallel ITL-...

Proteins are classified into families based on structural or functional similarities. Artificial intelligence methods such as Hidden Markov Models, Neural Networks and Fuzzy Logic have been used individually in the field of bioinformatics for tasks such as protein classification and microarray data analysis. We integrate these three methods into a...

� Abstract— One of the major problems in genomic field is to perform sequence comparison on DNA and protein sequences. Executing sequence comparison on the DNA and protein data is a computationally intensive task. Sequence comparison is the basic step for all algorithms in protein sequences similarity. Parallel computing is an attractive solution t...

The amount of biological information accessible via the internet is growing at a tremendous rate. The biologists often encounter problems in accessing huge amount of widely spread data due to disparate formats, remotely dispersed and varying implementation on different platforms and data models. Besides that, the custom browsing and querying mechan...

Clustering is a division of data into groups of similar objects. K-means has been used in many clustering work because of the ease of the algorithm. Our main effort is to parallelize the k-means clustering algorithm. The parallel version is implemented based on the inherent parallelism during the Distance Calculation and Centroid Update phases. The...

Proteins are classified into superfamilies based on structural or functional similarities. Neural networks have been used before to abstract the properties of protein superfamilies. One approach is to use a single conventional neural network to abstract the properties of different protein superfamilies. Since the number of protein superfamilies is...

Feature selection and extraction is the preprocessing step of image mining. An automatic shape recognition system by mining relevant image features is tested in this paper. The system is invariant to rotation, translation, size, and mirror effect and to a certain degree of distortion. Color, depth and texture grouped together to form a set of new f...

The design of a general purpose artificial vision system capable of recognizing arbitrarily complex three- dimensional objects without human intervention is still a challenging task in computer vision. Experiments have been conducted to test the ability of incorporating the knowledge of how human vision system works in a three- dimensional object r...

The advances in mobile phone technology have enabled such devices to be programmed to run general-purpose applications using a special edition of the Java programming language. Java is designed to be a heterogeneous programming language targeting different platforms. Such ability when coupled with the provision of high-speed mobile Internet access...

The size, complexity and number of databases used for protein information have caused bioinformatics to lag behind in adapting to the need to handle this distributed information. Integrating all the information from different databases into one database is a challenging problem. Our main research is to develop a tool which can be used to access and...

Many researches have been carried out internationally and locally in determining the antimicrobial activity against human pathogens. Malaysian researches had established the antimicrobial activity in misai kucing, buah kepayang, hempedu bumi, ginger etc. Screening of antimicrobial agents from these natural resources is very tedious, time consuming...