<p>This paper contributes to the literature on voice-recognition in the context of non-English language. Specifically, it aims to validate the techniques used to present the basic characteristics of speech, viz. voiced and unvoiced, that need to be evaluated when analysing speech signals. Zero Crossing Rate (ZCR) and Short Time Energy (STE) are used in this paper to perform signal pre-processing of continuous Malay speech to separate the voiced and unvoiced parts. The study is based on non-real time data which was developed from a collection of audio speeches. The signal is assessed using ZCR and STE for comparison purposes. The results revealed that ZCR are low for voiced part and high for unvoiced part whereas the STE is high for voiced part and low for unvoiced part. Thus, these two techniques can be used effectively for separating voiced and unvoiced for continuous Malay speech.</p>
Dijkstra algorithm is important to be understood because of its many uses. However, understanding it is challenging. Various methods to teach and learn had been researched, with mixed results. The study proposes questionled approach of the algorithm in a game-based learning context. The game designed based on an existing game model, developed and tested by students. Pre- and post-game tests compared and game feedback survey analysed. Results showed that students’ performance in graph data structure Dijkstra algorithm improved after playing the game where post-test mark was higher than pre-test. Game feedback were mostly positive, with areas of improvement. Students may use the game as a learning tool for self-regulated learning. Educators may get some ideas on how to design teaching tool using question-led approach.
<p class="0abstract">Data structure and algorithm is an important course in computer science and information technology programs, applied in almost all courses. Failure to master it will affect student's academic performance during study, getting job interviews, passing job interviews, and create an inefficient information technology worker. However, learning data structure is a worldwide problem because of its complex nature. Gameful visualization of data structures’ algorithms has been gaining momentum as it resulted in increased motivation, engagement and learning outcome. But effectiveness of game-based learning could be hindered if improper learning strategies used. Instructional scaffold in game-based learning in the form of question prompts have been found to be the most effective way to scaffold self-learn in computer-based learning. Thus, a game-based learning of stack data structure using question prompts was designed, developed and tested based on an adopted model to help students understand the algorithms of stack’s insert and delete operations for array implementation with gameplay that could create meaningful learning. A pre-game and post-game test was conducted to compare students’ performance on the topic. Results indicated a generally positive outcome.</p>
In this globalization era, smart mirror have been one of the invention to represent futuristic interconnected physical object with several applications. Smart mirror is innovating appliance that incorporates with contextual information which offered the interactive user interface on the surface of a mirror with the use of Raspberry Pi 3. To create this smart mirror the methodology that includes analysis about smart mirror, designing the hardware and software, developing the prototype, implementation and lastly the evaluation phases needs to be take care of. The presentation performed on the mirror will be information such as weather, time and date, holiday calendar, to-do list by mobile synchronization, current traffic of selected area, news feed and compliment as a motivation. Furthermore, our framework also introduces music presentation that use for alarm purpose. In a nutshell, this mirror what we called “Brilliant Reflect” will be convenient to use as it provides various features to the user.
This paper presents multi-instance (MI) image classification for cancer diagnosis using statistical mapping Support Vector Machine (SVM). The existing MI image classification is limited to focusing on standard multi-instance classification (MIC) assumption, but do not generalize to the whole range of MI data and do not fully utilize the power of conventional SVM. The standard MIC assumption labelled a bag of image as positive if there is at least one instance in it which is positive. Unfortunately, this assumption is not applicable if there is less information about abnormal instances provided in a bag. Therefore, the paper aims to propose conventional SVM that utilized the basic statistical mapping to form a bag vector of instances in order to classify MI images and give the benefit of the automated image diagnostic procedure. Numerical tests examine the benefit of instances' features transformation to be a vector of bag representation using mean and covariance mapping to Linear-SVM, Square-SVM and Cube-SVM. The experiments used a secondary dataset. The numerical dataset extracted breast histopathology image of 58 patients, which contains 708 features and 2002 instances. The result obtained shows that the proposed SVM can achieve 100% sensitivity after utilizing the covariance mapping with Square-SVM. It means the classification task able to detect the malignant class. In conclusion, the conventional SVM has great potential to improve medical diagnostic procedure using MI image, particularly for cancer diagnostic after adapting statistical features transformation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.