Syed Ahmad Aljunid

A novel hybrid fuzzy-SVM image steganographic model

This paper reviews the current soft computing (SC) techniques employed in image steganography as well as proposes a new hybrid approach of these SC techniques to exploit their complementary strengths. Four main SC techniques in image steganography — neural network (NN), genetic algorithm (GA), support vector machines (SVM) and fuzzy logic (FL) are assessed based on the three main measurements of steganography — imperceptibility, payload capacity and robustness. Most NN usage focuses on robustness, as well as the imperceptibility of the coverimage by exploiting its learning capability to produce a higher quality stego-image. GA is mostly employed to increase the payload capacity to be embedded as well as to find the best bit positions for embedding position in image steganography. SVM is normally used to increase the imperceptibility of the stego image via its strength to classify the image blocks by learning the relationship between the secret-message and cover-image to be used in the embedding and extracting procedures. A few works have been done in FL especially in preserving the imperceptibility and the number is increasing. Based on this review and leveraging the complementary strengths of FCM in clustering and SVM in classification, we propose a novel hybrid fuzzy c-means (FCM) and SVM (F-SVM) model in image steganography. The model uses the F-SVM as its main engine that is capable of embedding the secret-message imperceptible to human eyes while increasing the payload capacity. Currently, work is being done to develop and test this model.

Mobile Cloud Computing Testing Review

As mobile cloud computing applications are becoming widely used to mitigate the limitations of mobile devices and exploit cloud services, testing these applications becomes critical. Testing mobile cloud application is complicated further due to dynamic assign of cloud resource to applications that run on mobile devices, due to the increased multiple factors in test case generations and execution. This paper will critically review the three related areas of mobile, cloud and mobile cloud applications testing, in terms of features and models. Furthermore, it will show the necessity of a mobile cloud computing applications testing model due to its uniqueness from both native mobile application testing models and cloud applications testing models. Based on this review, although testing mobile cloud computing applications is critical, there is currently no model to test mobile cloud computing applications.

An experimental evaluation of scaffolded educational games design for programming

The effectiveness of educational games design has been the issue of many researches in recent years to support Computer Science (CS) novices, especially in the context of learning introductory programming courses. This issue has been highlighted due to the difficulties faced by students in developing algorithms related to programming concept, program construction as well as understanding and applying programming control structures. To overcome the identified difficulties and improve teaching and learning of programming, a number of research works have proposed educational games to motivate and engage their novices. However, to our knowledge, past research had applied general scaffolding characteristics in their games, but none has adapted these characteristics in the context of educational games design. As a result, three scaffolded educational games design characteristics are adapted to be embedded into our games. As proof of concept, a number of puzzle-based educational games which focus on decision-making structures are redesigned and redeveloped for teaching and learning programming. To validate the design, an experiment is conducted to 30 CS novices, who are randomly assigned into control and experimental groups. The results showed the educational games design-scaffolding characteristics are perceivably effective in assisting CS novices in learning programming. Therefore, the findings suggest these scaffolding characteristics have successfully been embedded as an effective educational games design technique.

SVM-SS Watermarking Model for Medical Images

To ensure the crucial integrity and confidentiality of patients’ information, this paper proposes a novel support vector machine (SVM) cum spread spectrum (SS) watermarking model to watermark medical images. In applying watermarking to secure medical images, there are generally three key stages, namely classifying the medical images into Region of Interest (ROI) and Region of Non-Interest (RONI), embedding the patients’ information and other relevant information into the image, and lastly extracting that information from the watermark images. The classifying and embedding stages require specific techniques tailored to their different requirements while the third is usually done using symmetric algorithms applied in the embedding stage. Among the soft computing techniques, SVM excels in classification including image classification and has a high potential to be used in the watermarking to improve its performance. However, based on current works reviewed in medical image watermarking, none has applied SVM yet. Similarly, SS is robust to the most common of signal processing and geometric distortions have been successfully applied in image watermarking. Therefore, in our novel model, SVM will be applied in the first stage while SS will be applied in the second and third stages. Significantly, the model aims to secure medical images to resist distortion as well as to avoid medical images quality degradation. The patient confidential data will be embedded into the RONI of their medical images using grayscale JPEG format using the SS symmetric algorithm. The watermark images will be evaluated on robustness and imperceptibility. Experiments will be conducted to measure the similarity ratio (SR) to test the robustness and Peak Signal to Noise Ratio (PSNR) to test the imperceptibility. The results show a high quality robust and imperceptible watermarking has been achieved with SR of more than 0.98 and PSNR of more than 40dB.

Application of Back Propagation Neural Network and ANFIS in forecasting university program

In recent years, intelligent techniques like Artificial Neural Network (ANN) and Fuzzy Logic (FL) have been adopted and tested to solve the real-world problems. The combination of those two powerful approaches has resulted in the emergence of Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS itself has achieved a rapid growth in its numbers of applications especially in control system, decision making, classification, forecasting, and modeling. Thus, in this paper, a study has been conducted to analyze and compare ANFIS and BPNN approaches in order to classify the SPM results for diploma programs in Universiti Teknologi MARA (UiTM), Malaysia. Each model has three input data from the public examination, Sijil Pelajaran Malaysia (SPM) results. They are clustered into three parameters, that are, sciences, mathematics and others and one output which is the academic marks for respective UiTM diploma programs. The Root Mean Square Error (RMSE) of the data set is computed in order to observe the accuracy of both models using the same data set. The testing RMSE for ANFIS and BPNN models are 5.6861 and 38.2040 respectively. Consequently, the findings indicate that ANFIS model can successfully forecast the UiTM diploma programs according to their SPM results better than BPNN.

Taxonomy of C overflow vulnerabilities attack

Various software vulnerabilities classifications have been constructed since the early 70s for correct understanding of vulnerabilities, and thus acts as a strong foundation to protect and prevent software from exploitation. However, despite all research efforts, exploitable vulnerabilities still exist in most major software, the most common still being C overflows vulnerabilities. C overflow vulnerabilities are the most frequent vulnerabilities to appear in various advisories with high impact or critical severity. Partially but significantly, this is due to the absence of a source code perspective taxonomy to address all types of C overflow vulnerabilities. Therefore, we propose this taxonomy, which also classifies the latest C overflow vulnerabilities into four new categories. We also describe ways to detect and overcome these vulnerabilities, and hence, acts as a valuable reference for developers and security analysts to identify potential security C loopholes so as to reduce or prevent exploitations altogether.

Secret Sharing Deniable Encryption Technique

Deniable Encryption was introduced to ensure that the sender and/or receiver in the communication able to create and encrypt fake messages into different ciphertexts to protect the real messages from a coercing adversary. Numerous past works have been proposed to cater the issues of coercible communication. To date, only Bi-Deniable Encryption has catered the issue of sender and receiver coercion. However there can be more than one receiver in a communication at a time. Multi-Party Computation addresses the problem of dishonest users that can be corrupted by the adversary. In some cases, Deniable Encryption may fails due to the coercer already know that it is applied in the communication protocol. A new deniability technique is needed to solve these problems. This research proposed Secret Sharing Deniable Encryption Technique. Secret Sharing technique is used to hide the secret key by creating shares and distributed among users.

Scaffolded Arabic language mobile educational game

Malaysian Muslims have been facing numerous difficulties in learning Arabic language. This problem has inevitably caused them complications in understanding the basic meanings of Al-Quran words and sentences. Presently, there exists a local technique named Al Furqan, based entirely on surahs from the Al-Quran that teaches Malaysian Muslims in classes to learn Arabic easily without much memorizing and writing, and without any homework. However, the element of interaction and engagement prior and after classes is missing. There is a learning gap which can be filled by mobile learning. Thus, this research work aims to design, develop and test a scaffolded mobile educational game called Easy Arabic for learning Arabic using the Al Furqan technique. The research is based on the developmental approach and consists of four major phases which are theoretical study, prototype design, prototype development and prototype testing. The prototype has been successfully developed and installed on Android platform, and has been tested by a sample of 30 Al Furqan learners. Most of them found this prototype significantly helpful in bridging the learning gap of understanding the basic technique of Al Furqan prior and after classes.

The design and development of intelligent university program ranking system using JEE frameworks

Web based systems have become the common medium of delivering software applications. Thus, developing web based systems has become a major concern for developers due to the large number of technologies, tools and techniques available today. Developers are often faced with the dilemma of choosing the best technology for their projects especially when developing a high quality system that must comply with certain standards. Enterprise developers often use development frameworks to simplify development job, and to insure that their code follows proven development methodologies. In this paper we describe our approach for developing an intelligent university program ranking system, using a JEE web application framework that has been developed utilizing industry standards and best practices. The development has been done using a well designed JEE web application framework and REpresentational State Transfer (REST) web services to minimize the development time and effort. The system which uses the powerful Adaptive Neuro-Fuzzy Inference System (ANFIS) algorithm for its AI engine is developed using the SEAM framework and RESTEasy web services framework. SEAM has been chosen due to its power and integration capabilities while RESTEasy framework is chosen for its seamless integration with JBoss SEAM. The developed system known as i-Selangkah is divided into two major components; a web based control panel to administer and modify the system as well as the programs fuzzy rules, and a web services interface to provide the existing Selangkah system with the ranking services. i-Selangkah has been successfully implemented, integrated and tested with the existing Selangkah system developed by UiTM. The tests showed that the system can effectively be used together with Selangkah to provide better program advising to these potential applicants with respect to their merit points, the specific and ever-changing program requirements and more significantly, the past intake trends.

Understanding vulnerabilities by refining taxonomy

Since early 90s, experts have proposed various ways to prevent exploitations and avoid releasing software with vulnerabilities. One way is through educating developers with information on known vulnerabilities using taxonomy of vulnerabilities as a guide. However, the guide using taxonomy of vulnerabilities has not shown to mitigate the issues. One possibility is due to the existence of gaps in producing the right and comprehensive taxonomy for software vulnerabilities. We studied various available taxonomies on software vulnerabilities. In this paper we propose and discuss our own criteria for taxonomy of software vulnerabilities with some improvement with particular emphasis on C programming.