Garuda - Garba Rujukan Digital

p-Index From 2020 - 2025

1.006

P-Index

This Author published in this journals

All Journal IAES International Journal of Artificial Intelligence (IJ-AI) TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Indonesian Journal of Electrical Engineering and Computer Science

Usman Ullah Sheikh

Universiti Teknologi Malaysia

Author-ID : 2406436

Computer Science & IT Electrical & Electronics Engineering Engineering

Published : 8 Documents Claim Missing Document

Claim Missing Document

Articles

Sentiment analysis of informal Malay tweets with deep learning Ong Jun Ying; Muhammad Mun'im Ahmad Zabidi; Norhafizah Ramli; Usman Ullah Sheikh
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 9, No 2: June 2020
Publisher : Institute of Advanced Engineering and Science

Twitter is an online microblogging and social-networking platform which allows users to write short messages called tweets. It has over 330 million registered users generating nearly 250 million tweets per day. As Malay is the national language in Malaysia, there is a significant number of users tweeting in Malay. Tweets have a maximum length of 140 characters which forces users to stay focused on the message they wish to disseminate. This characteristic makes tweets an interesting subject for sentiment analysis. Sentiment analysis is a natural language processing (NLP) task of classifying whether a tweet has a positive or negative sentiment. Tweets in Malay are chosen in this study as limited research has been done on this language. In this work, sentiment analysis applied to Malay tweets using the deep learning model. We achieved 77.59% accuracy which exceeds similar work done on Bahasa Indonesia.

HEVC 2D-DCT architectures comparison for FPGA and ASIC implementations Ainy Haziyah Awab; Ab Al-Hadi Ab Rahman; Mohd Shahrizal Rusli; Usman Ullah Sheikh; Izam Kamisian; Goh Kam Meng
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 5: October 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i5.12815

This paper compares ASIC and FPGA implementations of two commonly used architectures for 2-dimensional discrete cosine transform (DCT), the parallel and folded architectures. The DCT has been designed for sizes 4x4, 8x8, and 16x16, and implemented on Silterra 180nm ASIC and Xilinx Kintex Ultrascale FPGA. The objective is to determine suitable low energy architectures to be used as their characteristics greatly differ in terms of cells usage, placement and routing methods on these platforms. The parallel and folded DCT architectures for all three sizes have been designed using Verilog HDL, including the basic serializer-deserializer input and output. Results show that for large size transform of 16x16, ASIC parallel architecture results in roughly 30% less energy compared to folded architecture. As for FPGAs, folded architecture results in roughly 34% less energy compared to parallel architecture. In terms of overall energy consumption between 180nm ASIC and Xilinx Ultrascale, ASIC implementation results in about 58% less energy compared to the FPGA.

Recognition of vehicle make and model in low light conditions Aymen Fadhil Abbas; Usman Ullah Sheikh; Mohd Norzali Haji Mohd
Bulletin of Electrical Engineering and Informatics Vol 9, No 2: April 2020
Publisher : Institute of Advanced Engineering and Science

This paper presents a method for vehicle make and model recognition (MMR) in low lighting conditions. While many MMR methods exist in the literature, these methods are designed to be used only in perfect operating conditions. The various camera configuration, lighting condition, and viewpoints cause variations in image quality. In the presented method, the vehicle is first detected, image enhancement is then carried out on the detected front view of the vehicle, followed by features extraction and classification. The performance is then examined on a low-light dataset. The results show around 6% improvement in the ability of MMR with the use of image enhancement over the same recognition model without image enhancement.

Malaysian car plate localization using region-based convolutional neural network Tay Eng Liang; Usman Ullah Sheikh; Mohd Norzali Haji Mohd
Bulletin of Electrical Engineering and Informatics Vol 9, No 1: February 2020
Publisher : Institute of Advanced Engineering and Science

Automatic car plate localization and recognition system is a system that identifies the car plate location and recognizes the characters on the car plate input images. Within the automated system, the car plate localization stage is the first stage and is the most crucial stage as the success rate of the whole system depends heavily on it. In this paper, a Malaysian car plate localization system using Region-based Convolutional Neural Network (R-CNN) is proposed. Using transfer learning on the AlexNet CNN, the localization was greatly improved achieving best precision and recall rate of 95.19% and 97.84% respectively. Besides, the proposed R-CNN was able to localize car plates in complex scenarios such as under occlusion.

Hardware design of a scalable and fast 2-D hadamard transform for HEVC video encoder Heh Whit Ney; Ab Al-Hadi Ab Rahman; Ainy Haziyah Awab; Mohd Shahrizal Rusli; Usman Ullah Sheikh; Goh Kam Meng
Indonesian Journal of Electrical Engineering and Computer Science Vol 15, No 3: September 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v15.i3.pp1401-1410

This paper presents the hardware design of a 2-dimensional Hadamard transform used the in the rate distortion optimization module in state-of-the-art HEVC video encoder. The transform is mainly used to quickly determine optimum block size for encoding part of a video frame. The proposed design is both scalable and fast by 1) implementing a unified architecture for sizes 4x4 to 32x32, and 2) pipelining and feed through control that allows high performance for all block sizes. The design starts with high-level algorithmic loop unrolling optimization to determine suitable level of parallelism. Based on this, a suitable hardware architecture is devised using transpose memory buffer as pipeline memory for maximum performance. The design is synthesized and implemented on Xilinx Kintex Ultrascale FPGA. Results indicate variable performance obtained for different block sizes and higher operating frequency compared to a similar work in literature. The proposed design can be used as a hardware accelerator to speed up the rate distortion optimization operation in HEVC video encoders.

Distant temperature and humidity monitoring: prediction and measurement Farrukh Hafeez; Usman Ullah Sheikh; Attaullah Khidrani; Muhammad Akram Bhayo; Saleh Masoud Abdallah Altbawi; Touqeer Ahmed Jumani
Indonesian Journal of Electrical Engineering and Computer Science Vol 24, No 3: December 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v24.i3.pp1405-1413

Sensing environmental measuring parameters has a pivotal role in our everyday lives. Most of our daily life activities depend upon environmental conditions. Accurate information about these parameters also helps in several industrial applications like ventilation rate calculation, energy prediction, stock maintenance in warehouses, and saving from harmful conditions. The emergence of machine learning can make it easy to predict such time series problems. This paper describes the design of a remotely controlled robotic car for measuring and predicting humidity and temperature. A customized app for accessing the robotic car is designed to indicate predicted and realtime measured values of humidity and temperature. A sensor installed builtin helps in the measurement. The recurrent neural network (RNN) model is used to predict humidity and temperature. For this purpose, experiments are carried out in both outdoor and indoor settings. Accuracy of 85% and 90% is achieved in an outdoor environment and indoor settings.

Adaptive random testing with total cartesian distance for black box circuit under test Arbab Alamgir; Abu Khari A’ain; Norlina Paraman; Usman Ullah Sheikh
Indonesian Journal of Electrical Engineering and Computer Science Vol 20, No 2: November 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v20.i2.pp720-726

Testing and verification of digital circuits is of vital importance in electronics industry. Moreover, key designs require preservation of their intellectual property that might restrict access to the internal structure of circuit under test. Random testing is a classical solution to black box testing as it generates test patterns without using the structural implementation of the circuit under test. However, random testing ignores the importance of previously applied test patterns while generating subsequent test patterns. An improvement to random testing is Antirandom that diversifies every subsequent test pattern in the test sequence. Whereas, computational intensive process of distance calculation restricts its scalability for large input circuit under test. Fixed sized candidate set adaptive random testing uses predetermined number of patterns for distance calculations to avoid computational complexity. A combination of max-min distance with previously executed patterns is carried out for each test pattern candidate. However, the reduction in computational complexity reduces the effectiveness of test set in terms of fault coverage. This paper uses a total cartesian distance based approach on fixed sized candidate set to enhance diversity in test sequence. The proposed approach has a two way effect on the test pattern generation as it lowers the computational intensity along with enhancement in the fault coverage. Fault simulation results on ISCAS’85 and ISCAS’89 benchmark circuits show that fault coverage of the proposed method increases up to 20.22% compared to previous method.

Significance of electrodermal activity response in children with autism spectrum disorder Awais Gul Airij; Rubita Sudirman; Usman Ullah Sheikh; Lee Yoot Khuan; Nor Aini Zakaria
Indonesian Journal of Electrical Engineering and Computer Science Vol 19, No 2: August 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v19.i2.pp1113-1120

The human Autonomic Nervous System (ANS) controls the body’s physiological responses such as heart rate, electrodermal activity, temperature, and pupil diameter. The physiological responses are increased in the presence of a stressing stimuli and this is a typical ANS response. However, in case of children with Autism Spectrum Disorder (ASD), they suffer from autonomic dysregulation as reported in past owing to their atypical ANS response. This study investigated the ANS response of children with ASD and compares it with the response of normal children. EDA response datasets of 35 children with ASD and 55 normal children were acquired with the help of E4 wristband at a sampling rate of 4Hz. The signals were preprocessed to remove artefacts and noise and later compared. Furthermore, an SVM classifier was also used to classify the EDA response signals of normal children and children with ASD. The obtained results highlight that the ANS response of children with ASD is atypical as their EDA response is blunt and shows no significant tonic and phasic changes in EDA levels in the presence of stressing stimuli. In addition to that, an accuracy of 75% was obtained using the LF kernel of SVM classifier. The study further unfolds the hypoactive sympathetic response of children with ASD during a stressing event. Furthermore, this will help in future to anticipate the emotional responses of children with ASD such as anger, happiness, and anxiety.

Co-Authors Ab Al-Hadi Ab Rahman Abu Khari A’ain Ainy Haziyah Awab Arbab Alamgir Attaullah Khidrani Awais Gul Airij Aymen Fadhil Abbas Farrukh Hafeez Goh Kam Meng Heh Whit Ney Izam Kamisian Lee Yoot Khuan Mohd Norzali Haji Mohd Mohd Shahrizal Rusli Muhammad Akram Bhayo Muhammad Mun'im Ahmad Zabidi Nor Aini Zakaria Norhafizah Ramli Norlina Paraman Ong Jun Ying Rubita Sudirman Saleh Masoud Abdallah Altbawi Tay Eng Liang Touqeer Ahmed Jumani

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search