Papers by RAFIKHA ALIANA A RAOF
Advanced Research in Applied Sciences and Engineering Technology
Image processing is the most effective method for enhancement and segmentation of tuberculosis ba... more Image processing is the most effective method for enhancement and segmentation of tuberculosis bacilli in sputum smear samples. Improper straining can result in poor screening results such as over-staining, under-staining, and blurred images. The goal is to find an image enhancement and segmentation technique that will prepare the image for feature extraction. There are still some shortcomings with existing method when it is implemented on Ziehl Neelsen images. In normal images, TB bacilli can be identified easily, but in blur and images with dark background, TB bacilli are sometimes hidden behind the sputum cells. Hence, the basic method of contrast enhancement is not enough to improve the contrast of TB bacilli as the object of interest within the image. In this study, the combination of local and partial contrast enhancement is proposed as the best method for image enhancement. Image segmentation can be accomplished using Otsu thresholding technique. Otsu's method is presente...
Journal of Physics: Conference Series
Journal of Advanced Research in Applied Sciences and Engineering Technology
Among the top 10 leading causes of mortality, tuberculosis (TB) is a chronic lung illness caused ... more 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 parall...
Journal of Physics: Conference Series, 2019
Image contrast and brightness for sputum slide images are among important factors that can affect... more Image contrast and brightness for sputum slide images are among important factors that can affect the accuracy of image analysis process. Microscopic images usually have the problem of low contrast and blurry, which are caused by a couple of factors such as uneven thickness of the slides and manual preparation of the slide in the first place. In this research, image enhancement procedure has been considered for either increasing the image quality, increasing the visibility of tubercle bacilli or to ease the segmentation process. Partial contrast technique is considered for the contrast enhancement method. The results show that the modified technique helps to improve tubercle bacilli visibility. Hence the resulted images would become useful for the microbiologists and technologists for further analysis of Ziehl-Neelsen (ZN) sputum slide.
IOP Conference Series: Materials Science and Engineering, 2018
Cache replacement policies in chip multiprocessors (CMP) have been investigated extensively and p... more Cache replacement policies in chip multiprocessors (CMP) have been investigated extensively and proven able to enhance shared cache management. However, competition among multiple processors executing different threads that require simultaneous access to a shared memory may cause cache contention and memory coherence problems on the chip. These issues also exist due to some drawbacks of the commonly used Least Recently Used (LRU) policy employed in multiprocessor systems, which are because of the cache lines residing in the cache longer than required. In image processing analysis of for example extra pulmonary tuberculosis (TB), an accurate diagnosis for tissue specimen is required. Therefore, a fast and reliable shared memory management system to execute algorithms for processing vast amount of specimen image is needed. In this paper, the effects of the cache replacement policy in a partitioned shared cache are investigated. The goal is to quantify whether better performance can be achieved by using less complex replacement strategies. This paper proposes a Middle Insertion 2 Positions Promotion (MI2PP) policy to eliminate cache misses that could adversely affect the access patterns and the throughput of the processors in the system. The policy employs a static predefined insertion point, near distance promotion, and the concept of ownership in the eviction policy to effectively improve cache thrashing and to avoid resource stealing among the processors.
Journal of Physics: Conference Series, 2021
A plasmonic tracker had been developed for a plasmonic energy detection. It serves to determine r... more A plasmonic tracker had been developed for a plasmonic energy detection. It serves to determine resonance angle and refractive index of a dielectric material. A microstepping is required for scanning the reflected beam at a high resolution. Therefore, a precise control is crucial to align the photodiode parallel to the reflected laser beam at smallest angle displacement in a single rotation. The objective are to: 1- Synchronize two bipolar stepper motors for annular / rotational stage via the microstepping, 2- Determine the delay interval with Mamdani’s FIS and 3-Evaluate the Fuzzy Logic Controller in the MATLAB Simulink interface. Hybridization of Mamdani’s Fuzzy Logic was applied to determine appropriate delay interval for the Plasmonic Tracker. Two input variables and one output variable respectively were defined as Error, Change Error and Delay. Time delays interval were varied from 0.1s to 1s for synchronizing different microstepping resolution. The annular / rotary stages cater 8000 / 3200 microsteps at 0.045° / 0.1125° at a single rotation. Both stages cater a 7.5 ms per cycle for 360° span of angular interrogation within 60 second. Therefore, step sizes is matched with gear ratio of 2.5 with respective pulse for rotary stage / annular stage were 1 ms and 2 ms / 3 ms per cycle. MATLAB results was compared to centroid calculation and Simulink results The Fuzzy logic had demonstrates an efficient control, instant response and outstanding conversion based on the expert rule-based system.
Breast cancer is the most common cancer among women and it is one of the main causes of death for... more 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 multi-stage 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, ...
IOP Conference Series: Materials Science and Engineering, 2018
LoRa is a low power long range wireless communication platform that is designed as an efficient c... more LoRa is a low power long range wireless communication platform that is designed as an efficient communication platform for small, low powered devices. This makes it very suitable for battery powered devices and IoT implementation. This paper evaluates some low cost LoRa modules available on the market and their suitability, energy efficiency and performance during operation. Two low cost LoRa transceiver from Semtech Industries, the SX1272 and SX1278 were tested for their power consumption and maximum transmission range. This study have evaluated the two LoRa solutions and found that the SX1278 have a better transmission range and uses lower energy compared to the SX1272 thus making it more suitable for embedded implementation as a data gateway.
Applied Mechanics and Materials, 2019
A gyro-stabilized antenna platform could implement a real-time motion compensation for a SAR syst... more A gyro-stabilized antenna platform could implement a real-time motion compensation for a SAR system. Since motion errors reduce during the data acquisition process, post-processing load also reduces. Subsequently, production of well-focused, and high-resolution synthetic aperture radar (SAR) images is conceivable. The research is to design a gyro-stabilized SAR antenna platform that compensates motion in real time during data acquisition. This paper explains the study of undesired motion (error) for typical UAV SAR. The resulting angle ranges of yaw, pitch, and roll describe the magnitude of the motion errors. The design of a gimbal system as a stable antenna platform considers yaw, pitch and roll range parameters. IMU optimization (Complimentary Filter, and Madgwick Filter algorithms are tested and compared in order to decide the optimum optimization scheme for the antenna platform. The data fusion and gradient descent algorithm from Madgwick show significant performance. The imple...
Indonesian Journal of Electrical Engineering and Computer Science, 2019
This study presents characterization of cracking in pavement distress using image processing tech... more This study presents characterization of cracking in pavement distress using image processing techniques and k-nearest neighbour (kNN) classifier. The proposed semi-automated detection system for characterization on pavement distress anticipated to minimize the human supervision from traditional surveys and reduces cost of maintenance of pavement distress. The system consists of 4 stages which are image acquisition, image processing, feature extraction and classification. Firstly, a tool for image acquisition, consisting of digital camera, camera holder and tripod, is developed to capture images of pavement distress. Secondly, image processing techniques such as image thresholding, median filter, image erosion and image filling are applied. Thirdly, two features that represent the length of pavement cracking in x and y coordinate system namely delta_x and delta_y are computed. Finally, the computed features is fed to a kNN classifier to build its committee and further used to classif...
2009 IEEE International Conference on Signal and Image Processing Applications, 2009
10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010), 2010
Uploads
Papers by RAFIKHA ALIANA A RAOF