N. B. Mohamad

Comparison between Levenberg-Marquardt and Scaled Conjugate Gradient training algorithms for Breast Cancer Diagnosis using MLP

Computerized diagnostic tools have received significant attention over the past few decades, in order to assist medical practitioners in diagnosis of disease based on a variety of test results. It provides a fast and accurate method for diagnosis, particularly in cases where medical practitioners need to deal with difficult diagnosis problems. In this paper, we present an examination of two popular training algorithms (Levenberg-Marquardt and Scaled Conjugate Gradient) for Multilayer Perceptron (MLP) diagnosis of breast cancer tissues. We test the performance of the training algorithms using features extracted from the Wisconsin Breast Cancer Database (WBCD), a benchmark dataset that has been extensively used in literature for breast cancer diagnosis. Based on our results, we conclude that both algorithms were comparable in terms of accuracy and speed. However, the LM algorithm has shown slightly better advantage in terms of accuracy (as evidenced in the average training accuracy and MSE) and speed (as evidenced in the average training iterations) on the best MLP structure (with 10 hidden units).

Wavelet Packet analysis of EEG signals from children during writing

EEG Signal has been used to identify the brain activity involved during writing for children with dyslexia. Conventionally, the MRI and PET were used to analyse the brain activity of children diagnosed with dyslexia. EEG signal has non-stationary and complex characteristic. Since Wavelet Packet Decomposition technique has orthogonality property that can prevent aliasing, it was used in this study to analyse the EEG signals from dyslexic and normal children. It was found that the left brain hemisphere is more active for dyslexic children during writing. Results showed that there is no difference in alpha band frequency spectrum during relax and writing activity for dyslexic children. However, alpha band for normal children has higher amplitude during relax than that during writing. During writing, the amplitude of beta sub-band of dyslexic children is higher than that of normal children.

EEG-based time and spatial interpretation of activation areas for relaxation and words writing between poor and capable dyslexic children

Symptoms of dyslexia such as difficulties with accurate and/or fluent word recognition, and/or poor spelling as well as decoding abilities, are easily misinterpreted as laziness and defiance amongst school children. Indeed, 37.9% of 699 school dropouts and failures are diagnosed as dyslexic. Currently, Screening for dyslexia relies heavily on therapists, whom are few and subjective, yet objective methods are still unavailable. EEG has long been a popular method to study the cognitive processes in human such as language processing and motor activity. However, its interpretation is limited to time and frequency domain, without visual information, which is still useful. Here, our research intends to illustrate an EEG-based time and spatial interpretation of activated brain areas for the poor and capable dyslexic during the state of relaxation and words writing, being the first attempt ever reported. From the 2D distribution of EEG spectral at the activation areas and its progress with time, it is observed that capable dyslexics are able to relax compared to poor dyslexics. During the state of words writing, neural activities are found higher on the right hemisphere than the left hemisphere of the capable dyslexics, which suggests a neurobiological compensation pathway in the right hemisphere, during reading and writing, which is not observed in the poor dyslexics.

An analysis of EEG signal power spectrum density generated during writing in children with dyslexia

Power spectral density is one of the possible feature extraction methods to identify differences in the brain electrophysiological processing in children with dyslexia. Known to be a neurological disorder, dyslexia causes learning deficiencies mostly related to reading, although research has shown that writing problems also poses significant challenge and is a good indicator to identify a child to be dyslexic. This research looks into the analysis of electroencephalogram (EEG) signal power spectrum density (PSD) during resting and writing activities of a poor dyslexic and capable dyslexic children. Activities include writing of known words based on cues from a computer. Eight electrodes position were localized that are based on pathway known for reading and writing, which are C3, C4, P3, P4, T7, T8, FC5 and FC6, where location of the right hemisphere were mirrored. Analysis showed that the PSD of the frontal right hemispheric locations in capable dyslexic children is significantly higher if compared to the left while poor dyslexics showed higher results in areas to the left. This can be viewed as the brain is compensating its left deficiencies with creating a new pathway that involved areas of the frontal right hemisphere.

Selection of Symlets wavelet function order for EEG signal feature extraction in children with dyslexia

Electroencephalograph (EEG) signal provides information on brain functionalities where electrodes are placed on the surface of the scalp and is suitable in analyzing neurological based disorder such as dyslexia. Known to cause learning disorder, dyslexic tends to utilize different areas of the brain in processing information compared to that of a normal learner. Being non-stationary, the wavelet theory has been extensively used in extracting relevant features from the noisy EEG signal with a wide option of wavelet families. The aim of this paper is to identify a suitable function order within the Symlets family to extract power feature in the EEG signal of dyslexic children during writing. Recorded EEG signals from 8 electrode locations of C3, C4, P3, P4, FC5, FC6, T7 and T8 were analyzed using Symlets function of order 5, 7, 8 and 9. The final selection are based on the order ability to provide the most distinctive variance and consistency in term of its beta band power feature. Results indicated that Symlets of order 5 and 7 (Sym-5, Sym-7) are suitable for extracting power band feature for EEG signal of poor dyslexic children during writing. However, results with capable dyslexic children were inconsistent.

Malaysia Design Industry: Profile of the Malaysia Design Businesses 2013

This research has been done to specifically look at one part of the survey which is the profile of the Malaysia Design Businesses that has been done in 2013. About 70 questionnaires from different design companies were used in this survey. Some parts of the profile design businesses in Malaysia that we are looking at is the location of the design companies, years that the company has been operating and the number of designers and freelance designers that the company is hiring, whether male or female dominates the Design Industry and to also look at what discipline of the businesses that they do. The key findings of this research are being explained in each section. This research is also looking at how the industry values the design (Bicknell and Mcquiston 1977; Aspelund 2006; Hannula et al. 2005) and designers (Bevlin 1989) that operate the businesses and also potential market for the growth of the Design Industry in Malaysia. Questions of where the students of Art and Design will lead them in their career will be answered by looking at the results and findings of this survey.

2D-EEG Topography and fMRI Brain Images for Relaxation and Letter Writing

Electroencephalography (EEG) can localize neural electrical activity and track in vivo brain functions in milliseconds with high temporal resolution. Even though EEG is said to be time accurate and spatial inaccurate, the approximate spatial information is still useful. In view of the shortcomings of imaging modalities, the purpose of our work is to propose EEG as a potential neurofeedback protocol since it can provide concurrent feedback and progressive states of neuronal activation. The preliminary work here intends to study the correspondence between the 2D EEG topography and brain images from fMRI for the normal adults during relaxation state and letter writing, being the first attempt ever reported. With OpenViBE as the platform, the EEG signal acquired was segmented, filtered and extracted for significant features, before the EEG topography is generated. Despite difficulty in finding the corresponding brain images, it is found that the EEG topography along the reading-writing pathway is a close match to images from fMRI studies and neurological theories.

Normal and dyslexic children: EEG topography versus fMRI brain images during letters writing

Dyslexia is a neurological disorder that needs to be detected at an early stage. It is defined as difficulty with learning due to impairment of the left hemisphere of the brain associated with language processing. The excellent time resolution of electroencephalography (EEG) provides a unique window on the dynamics of the human brain functions. Even though EEG is said to be time accurate and spatial inaccurate, the approximate spatial information is still useful. In this paper, we presented initial work to study correspondence between the 2D EEG topography and brain images from fMRI for the normal and dyslexic children during letters writing, being the first attempt ever reported. Under the OpenViBE programming environment, the EEG signal acquired was filtered and extracted for significant features, before the EEG 2D topography is generated. Despite difficulty in finding the corresponding brain images, it is found that the 2D EEG topography along the reading-writing pathway for normal and dyslexic children, is a close match to images from previous fMRI studies and neurological theories. Differences in hemispheric activation are found, between normal, dyslexic Capable and dyslexic Poor children.

“Formal, Medium, and Subject Matter” from the Content Making Framework

This research which is the third part of four will be an extensive elaboration on the second principles which is “Formal, Medium, and Subject Matter,” newly reviewed and formed from the initial structure created in the first part of the research which was “Formal (Subject Matter), Material, and Meaning.” The elaboration was done through cross-referencing and interpreting several literatures especially that of Barrett (2011) Making Art: Form and Meaning and Lazzari and Schlesier (2008) Exploring Art: A Global, Thematic Approach. The objective of this paper was to elaborate and explicate the meaning of the second principle so that fine art students can use it as a form of conceptual construction and guideline in establishing their own understanding of formal, medium, and inquiry subject matter.

Elaborating Context from the Content Making Framework

This research which is the second part will be an extensive elaboration on the newly formed content making framework. In the first part of the research, the research was conducted to establish and form a framework which looked into two “art interpretation” frameworks. One was from Lucy Lippard’s framework extracted by Cynthia Freeland, and the second was from Terry Barrett. Thus, in the second part of the three subseries, this paper will focus on explicating and elaborating the first key principle which is “context.” This was done through cross-referencing and interpreting several literatures especially that of Freeland (2003), Art Theory: A Very Short Introduction; Barrett (2011), Making Art: Form and Meaning; Heartney (2008), Art & Today; Robertson and McDaniel (2010), Themes of Contemporary Art: Visual Art after 1980; Lucie-Smith (1999), Art Today; Lazzari and Schlesier (2008), Exploring Art: A Global, Thematic Approach; Kalb (2013), Art Since 1980: Charting the Contemporary; and Collins (2007), Sculpture Today. Other non-printed key reference was a short-format documentary series from the Sollins and Dowling’s ART21 – seasons 1 until 6 (2001–2012).