Abstract--Word stemmer is one of the basic and crucial text processing tools in any languages. Word Stemmer Is not only useful In morphological study but also play an Important role in word level context analysis. Due to the existence of prefix, suffix, infix and a combination of affixes in Malay word, it raises the complexity of performing stemming to Malay word. An approach to stem Malay word using syllabification algorithm is Introduced. This approach performs stemming through comparing syllable in the word thus reduces the parsing processes. The approach shows high practicality as it produces a very high accuracy in the evaluation. This paper is organized as follows: the first section described the nature Malay word stemming process. Second section discussed previous related research on Malay word stemmer. The third section provides a step-by-step explanation on the proposed stemming method. Fourth section described the evaluation process and result of the evaluation. Fifth section discussed on the limitation of the proposed method based on the evaluation result. Sixth section mentions the future work that can expanded from the current study and the final section concludes the study for this paper.

The objective of this research is to develop the framework for sustainable land-use planning on the basis of seismic microzonation to reduce the devastating effects of future earthquakes by utilizing the software geographical information system (ArcGIS). Miri district of Sarawak in Malaysia has been chosen as the study area because of having the highest peak ground acceleration which is 0.09g in terms of the 10% probability of exceedance in 50 years. In addition, the frequency of an earthquake with a magnitude up to 5.3 is approximately every 5-7 years. Therefore, it is vital to introduce land use planning in order to diminish the adverse effects of earthquakes in the future. For this purpose, Google Earth Pro was used for the collection of satellite image data for land use planning purposes. From the results, it was found that the seismic hazard in the Miri district varies from low to high corresponding to 2475 years of return period with low to moderate as predominant over the Miri district. Only a few areas are under high hazard. Also, the land use planning map was compared with the current land use map acquired from satellite imagery and it was found that all built-up is in the low hazard area. It is envisaged that the findings from this research will contribute immensely to the literature that will serve as background information and a guide for analysts, disaster management, engineering designers and seismologists in Malaysia and the world as a whole.

Human Activity Recognition (HAR) focuses on detecting people's daily regular activities based on time-series recordings of their actions or motions. Due to the extensive feature engineering and human feature extraction required by traditional machine learning algorithms, they are timeconsuming to develop. To identify complicated human behaviors, deep learning approaches are more suited since they can automatically learn the features from the data. In this paper, a feature-fusion concept on handcrafted features and deep learning features is proposed to increase the recognition accuracy of diverse human physical activities using wearable sensors. The deep learning model Long-Short Term Memory based Deep Recurrent Neural Network (LSTM-DRNN) will be used to extract deep features. By fusing the handcrafted produced features with the automatically extracted deep features through the use of deep learning, the performance of the HAR model can be improved, which will result in a greater level of accuracy in the HAR model. Experiments conducted on two publicly available datasets show that the proposed feature fusion achieves a high level of classification accuracy.

No abstract

No abstract