Rafikha Aliana A Raof
Thumbnail Image
Preferred name
Rafikha Aliana A Raof
Official Name
Rafikha Aliana, A Raof
Alternative Name
Raof, Rafikha Aliana A.
Raof, R. A.A.
Raof, Rafikha Alaina A.
Main Affiliation
Scopus Author ID
57075005500

Research Output

Filters

6
6
Reset filters

Settings
Now showing 1 - 6 of 6
Thumbnail Image
Publication

Chatbot Application Training Using Natural Language Processing Techniques: Case of Small-Scale Agriculture

2024-06-07 , Ong R.J. , Rafikha Aliana A Raof , Suhizaz Sudin , Choong K.Y.

Tacit knowledge, which is based on first-hand experience and is more difficult to articulate, has evolved alongside natural languages as they are passed down through the years. In computing, Natural Language Processing (or NLP) refers to a set of methods for studying and modelling human languages that may be studied and represented automatically. Extracting or searching through vast bodies of unregulated text for specific information can be a complex and time-consuming process. Knowledge comes in several shapes and sizes, but can usually be differentiated into two types: structured or unstructured. Using NLP techniques, unstructured text data can be translated into a structured and well-organized database and then used for question-answering purposes. This paper is about the implementation of NLP techniques to convert unstructured text data into a structured database for Chatbot application training.

View
Thumbnail Image
Publication

Tuberculosis Classification Using Deep Learning and FPGA Inferencing

2023-02-01 , Fazrul Faiz Zakaria , Asral Bahari Jambek , Norfadila Mahrom , Rafikha Aliana A Raof , Mohd Nazri Mohd Warip , Al Eh Kan P.L. , Mustapa M.

Among the top 10 leading causes of mortality, tuberculosis (TB) is a chronic lung illness caused by a bacterial infection. Due to its efficiency and performance, using deep learning technology with FPGA as an accelerator has become a standard application in this work. However, considering the vast amount of data collected for medical diagnosis, the average inference speed is inadequate. In this scenario, the FPGA speeds the deep learning inference process enabling the real-time deployment of TB classification with low latency. This paper summarizes the findings of model deployment across various computing devices in inferencing deep learning technology with FPGA. The study includes model performance evaluation, throughput, and latency comparison with different batch sizes to the extent of expected delay for real-world deployment. The result concludes that FPGA is the most suitable to act as a deep learning inference accelerator with a high throughput-to-latency ratio and fast parallel inference. The FPGA inferencing demonstrated an increment of 21.8% in throughput while maintaining a 31% lower latency than GPU inferencing and 6x more energy efficiency. The proposed inferencing also delivered over 90% accuracy and selectivity to detect and localize the TB.

View
Thumbnail Image
Publication

Multi-stage feature selection (MSFS) algorithm for UWB-based early breast cancer size prediction

2020-08-01 , Vijayasarveswari V. , Allan Melvin Andrew , Muzammil Jusoh , Thennarasan Sabapathy , Rafikha Aliana A Raof , Mohd Najib Mohd Yasin , R Badlishah Ahmad , Khatun S. , Hasliza A Rahim @ Samsuddin

Breast cancer is the most common cancer among women and it is one of the main causes of death for women worldwide. To attain an optimum medical treatment for breast cancer, an early breast cancer detection is crucial. This paper proposes a multistage feature selection method that extracts statistically significant features for breast cancer size detection using proposed data normalization techniques. Ultra-wideband (UWB) signals, controlled using microcontroller are transmitted via an antenna from one end of the breast phantom and are received on the other end. These ultra-wideband analogue signals are represented in both time and frequency domain. The preprocessed digital data is passed to the proposed multistage feature selection algorithm. This algorithm has four selection stages. It comprises of data normalization methods, feature extraction, data dimensional reduction and feature fusion. The output data is fused together to form the proposed datasets, namely, 8-HybridFeature, 9-HybridFeature and 10-HybridFeature datasets. The classification performance of these datasets is tested using the Support Vector Machine, Probabilistic Neural Network and Naïve Bayes classifiers for breast cancer size classification. The research findings indicate that the 8-HybridFeature dataset performs better in comparison to the other two datasets. For the 8-HybridFeature dataset, the Naïve Bayes classifier (91.98%) outperformed the Support Vector Machine (90.44%) and Probabilistic Neural Network (80.05%) classifiers in terms of classification accuracy. The finalized method is tested and visualized in the MATLAB based 2D and 3D environment.

View
Thumbnail Image
Publication

Hybrid approach for vegetable price forecasting in electronic commerce platform

2024-06-01 , Choong K.Y. , Suhizaz Sudin , Rafikha Aliana A Raof , Ong R.J.

The significance of the agriculture sector in Malaysia is often overlooked, and there is a notable deficiency in the advancement of digitalization within the country’s agricultural domain. The integration of a price forecasting model in the platform enables the relevant parties, including farmers, to make informed decisions and plan their crop selection based on projected future prices. In this research, the authors proposed the hybrid approach with the combination of a linear model and a non-linear model in doing the vegetable price forecasting model. The hybrid model combining seasonal autoregressive integrated moving average (SARIMA)-discrete wavelet transform (DWT)-genetic algorithm neural network (GANN), referred to SARIMA-DWT-GANN, was used to forecast monthly vegetable prices in Malaysia. The historical vegetable price data is collected from the federal agricultural marketing authority Malaysia and split into training/test sets for modeling. The performance of the models is evaluated on the accuracy metrics including mean absolute error (MAE), mean absolute percentage error, and root mean square error (RMSE). The forecasted results using the proposed hybrid model are compared to those using the single SARIMA model. In conclusion, the hybrid SARIMA-DWT-GANN model is superior to the individual model, which obtained the smaller MAE and RMSE, and got the forecast accuracy of at least 95%.

View
Thumbnail Image
Publication

Dynamic web-based knowledge management system (KMS) in small scale agriculture

2024-02-08 , Ong R.J. , Suhizaz Sudin , Rafikha Aliana A Raof , Choong K.Y. , Azremi Abdullah Al-Hadi , Yacob Y. , Nasir S.N.B.M.

The shift from paper-based to web-based practice is a significant trend, as paper-based practice consumes time, is prone to error, and is more prone to data loss, all of which lead to inefficiency. Smart farming or agriculture 4.0 defined the new era of agriculture that moving toward digitalization. However, the absence of a centralized information system, which results in information asymmetry among agricultural sectors. One of the keys to success is reaching out to farmers with pertinent agricultural information at the appropriate time and platform. The purpose of this study is to design and create a dynamic web-based knowledge management system for the dissemination of agricultural knowledge in Malaysia. A centralized information system capable of achieving information symmetry, in which all important information is accessible to all participants. Creating an advanced learning environment allowing for virtual engagement between external and internal stakeholders via a web-based knowledge management system.

View
Thumbnail Image
Publication

Analysis On the Effect of The Length of Training and Test Set to The Accuracy of SARIMA Forecasting

2024-06-07 , Choong K.Y. , Rafikha Aliana A Raof , Suhizaz Sudin , Ong R.J.

The Seasonal Autoregressive Integrated Moving Average (SARIMA) models which built upon the ARIMA models to support seasonality, are used when it encounter the periodic time series data. It has been widely used in infectious disease prediction and other fields where data indicate a seasonal pattern. However, there are lacks of research focuses on the impact of the length of training and test data on the forecasting accuracy. In this study, the data is split into two parts: Training and Test data. The selected SARIMA model will be fitted for different lengths of training data and forecast the observations of the length of test data. This study aims to investigate how the length of training and test data affect the forecasting accuracy. In order to check it, the Mean Absolute Percentage Error (MAPE) for different lengths of training data are calculated and compared to study their relationship.

View