Oi-Mean Foong

TEXT SIGNAGE RECOGNITION IN ANDROID MOBILE DEVICES

This study presents a Text Signage Recognition (TSR) model in Android mobile devices for Visually Impaired People (VIP). Independence navigation is always a challenge to VIP for indoor navigation in unfamiliar surroundings. Assistive Technology such as Android smart devices has great potential to assist VIPs in indoor navigation using built-in speech synthesizer. In contrast to previous TSR research which was deployed in standalone personal computer system using Otsu’s algorithm, we have developed an affordable Text Signage Recognition in Android Mobile Devices using Tesseract OCR engine. The proposed TSR model used the input images from the International Conference on Document Analysis and Recognition (ICDAR) 2003 dataset for system training and testing. The TSR model was tested by four volunteers who were blind-folded. The system performance of the TSR model was assessed using different metrics (i.e., Precision, Recall, F-Score and Recognition Formulas) to determine its accuracy. Experimental results show that the proposed TSR model has achieved recognition rate satisfactorily.

OCR signage recognition with skew & slant correction for visually impaired people

It is a challenge for visually impaired people (VIPs) to navigate independently whenever they attempt to find their way in unfamiliar buildings searching for amenities (i.e. exits, ladies/gents toilets) even with a walking stick or a guide dog. Camera-based computer vision systems have the potential to assist VIPs in independent navigation or way finding in unfamiliar places. To leverage on previous research of Signage Recognition Framework which could only recognize public signage with slanted angle less than30°, an improved OCR signage recognition model with skew and slant correction in public signage is presented. The proposed OCR method consists of Canny edge detection algorithm, Hough Transformation and Shearing Transformation were used to detect and correct skewed and slanted images. The proposed model would capture a public signage image, compare the image in the database using template matching algorithm and convert to machine readable text in a text file. The text will then be processed by Microsoft Speech Application Program Interface (SAPI) speech synthesizer and translated to voice as output. Experiments were conducted on 5 blind folded subjects to test the performance of the model. The proposed OCR recognition model has achieved satisfactory recognition rate of 82.7%.

A hybrid PSO model in Extractive Text Summarizer

The World Wide Web has caused an information explosion. Readers are often drowned in information while starved of knowledge. Readers are bombarded with too many lengthy documents where shorter summarized texts would be preferable. This paper presents a hybrid Harmony Particle Swarm Optimization (PSO) framework in an Extractive Text Summarizer to tackle the information overload problem. Particle Swarm Optimization is a suitable technique for solving complex problems due to its simplicity and fast computational convergence. However, it could be trapped in a local minimal search space in the midst of searching for the optimal solutions. The objective of this research is to investigate whether the proposed hybrid harmony PSO model is capable of condensing original electronic documents into shorter summarized texts more efficiently and accurately than the alternative models. Empirical results show that the proposed hybrid PSO model improves the efficiency and accuracy of composing summarized text.

Text Summarization in Android Mobile Devices

This paper presents a text summarization in Android mobile devices. With the proliferation of small screen devices and advancement of mobile technology, the text summarization research has been inspired by the new paradigm shift in accessing information ubiquitously at anytime, anywhere and anyway on mobile devices. However, it is a challenge to browse large documents in a mobile device because of its small screen size and information overload problems. In this paper, a semantic and syntactic based summarization was attempted and implemented in a text summarizer. The objectives of the paper are two-fold. (1) To integrate WordNet 3.1 into the proposed system called TextSumIt which condenses single lengthy document into shorter summarized text. (2) To provide better readability to Android mobile users by displaying the salient ideas in bullets points. Documents were collected from DUC 2002 and Reuter news datasets. Experimental results show that the text summarization model improves the accuracy, readability and time saving in the text summarizer as compared with MS Word AutoSummarize.

Text Summarization Using Latent Semantic Analysis Model in Mobile Android Platform

This paper presents the Latent Semantic Analysis (LSA) Model in Automatic Text Summarization (ATS) on single English document in mobile Android platform. Readers are drowned in information while starved of knowledge. Millions of articles are uploaded into the website every day. Quite often, lengthy text are presented in online articles but shorter summarized texts are preferred by readers. There exists research gap as most of the extractive text summarizations are based on syntactic appearance of words. Thus, the objective of this paper is to investigate the LSA Model by examining the semantic relationship between terms and sentences in a document for text summarization. We intend to shift our research paradigm to summarize text to infer the semantic contextual cues using the co-occurrence of terms in text. The input text documents were downloaded from Document Understanding Conference 2002 dataset. The preliminary results show that the LSA model yields an average F-Score of 0.386 in text summarization.

An exploratory study on the user experience of foot reflexology therapy using reflexology artifacts

The reputation and significance of foot reflexology therapy has continuously been on the rise. It is currently widely used as a complementary therapy, for stress relief and a potential diagnostic tool. In the society nowadays, there exist a lot of reflexology artifacts that claim to be an alternative substitutes to the traditional foot reflexology practice since the practices promote relaxation and stress relief. However, there has been very little or no attention given towards the verification of such anecdote and the identification of the similarities, differences and opportunities these reflexology artifacts offer. This paper hence aims to address this issue through the exploration of the practices. The study examined the interactive nature of four different sets of common reflexology artifacts from both the patients’ and the experts’ perspective. Data were collected through audio recorded semi-structured interview. The study findings revealed answers to those anecdotes, highlighting the similarities, ...

MOBILE HEALTH AWARENESS IN PRE-DETECTION OF MILD STROKE SYMPTOMS

Stroke contributes to the third leading cause of death in Malaysia and happens to be the prime cause of disability among Malaysian. Lack of awareness and knowledge of stroke among Malaysian have often led to delay in hospital administration and reduced the chances of recovery for stroke patients. The objectives of this research are three-fold: (1) To develop a mobile application that helps to perform early detection on mild stroke symptoms (2) To increase the stroke awareness and knowledge level among the society (3) To create a reminder to constantly motivate the society to perform regular self-check on mild stroke symptoms. The mobile application is targeted for general public usage. Interviews were conducted with consultant neurologist and physiotherapist & rehabilitation manager of the National Stroke Association of Malaysia (NASAM). An online pre-survey has also been conducted among 70 random people to investigate the feasibility of the mobile application. The stroke pre-detection application was implemented in Android platform. The National Institute of Health Stroke Scale (NIHSS) will be used as a guideline for the development of self-check assessment for detecting mild stroke symptoms as it is proven to be reliable and effective evaluation technique. Empirical results show that majority of the respondents believe that the mobile stroke application can increase their stroke awareness and help them to perform early detections on mild stroke symptoms. The mobile stroke application performs satisfactorily in terms of its usefulness, usability, mobile application quality and information quality.

Simulation Study of Single Quantum Channel BB84 Quantum Key Distribution

With the increasing information being shared online, the vast potential for cybercrime is a serious issue for individuals and businesses. Quantum key distribution (QKD) provides a way for distribution of secure key between two communicating parties. However, the current Quantum Key Distribution method, BB84 protocol, is prone to several weaknesses. These are Photon-Number-Splitting (PNS) attack, high Quantum Bit Error Rate (QBER), and low raw key efficiency. Thus, the objectives of this paper are to investigate the impacts of BB84 protocol towards QBER and raw key efficiencies in single quantum channel. Experiments were set up using a QKD simulator that was developed in Java NetBeans. The simulation study has reaffirmed the results of QBER and raw key efficiencies for the single quantum channel BB84 protocol.

Droopy Mouth Detection Model in stroke warning

This paper presents a Droopy Mouth Detection Model in stroke warning. The objective of this paper is to take up the challenge to provide early detection of stroke through mouth drooping detection in mobile Android platform. To achieve that, a specialized library, Google Mobile Vision is utilized to detect facial landmark such as mouth corners and obtain the coordinates of the landmarks or key points for further processing. The inputs for the proposed droopy mouth detection model were taken from the Google Web Images and National Cheng Kung University (NCKU) Robotics Face datasets. The system prototype was evaluated using metrics such as Precision, Recall and F-Score to determine its recognition rate. Experimental results show that the proposed droopy mouth detection model has achieved satisfactory recognition rate.

Optimization of sensor deployment in data center

The demand for data center (DC) has been increasing significantly due to the rapid growth in ICT technology. This brings along the “green” issues in data center such as energy consumption, heat generation and cooling requirements. These issues can be addressed by “Green of/by IT” approach in the context of operating costs as well as the environmental impacts. To install temperature monitoring system in every corner of data center is certainly cost inefficient. Optimizing the number of sensors deployed in DC is thus important for reducing the monitoring cost. This project aims to create a wireless temperature monitoring system with an optimizing technique to optimize the number of temperature sensors deployed in a DC. The real-time temperature data collected by this system can also be used to predict the next state of the temperature in DC to detect potential anomaly in heat generation. Quick preventive response can thus be invoked to manage this potential hot spots in DC. This could be a promising green by IT approach.