Rozeha A. Rashid
Universiti Teknologi Malaysia

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

Machine learning based lightweight interference mitigation scheme for wireless sensor network Ali Suzain; Rozeha A. Rashid; M. A. Sarijari; A. Shahidan Abdullah; Omar A. Aziz
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 4: August 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i4.14879

Abstract

The interference issue is most vibrant on low-powered networks like wireless sensor network (WSN). In some cases, the heavy interference on WSN from different technologies and devices result in life threatening situations. In this paper, a machine learning (ML) based lightweight interference mitigation scheme for WSN is proposed. The scheme detects and identifies heterogeneous interference like Wifi, bluetooth and microwave oven using a lightweight feature extraction method and ML lightweight decision tree. It also provides WSN an adaptive interference mitigation solution by helping to choose packet scheduling, Acknowledgement (ACK)-retransmission or channel switching as the best countermeasure. The scheme is simulated with test data to evaluate the accuracy performance and the memory consumption. Evaluation of the proposed scheme’s memory profile shows a 14% memory saving compared to a fast fourier transform (FFT) based periodicity estimation technique and 3% less memory compared to logistic regression-based ML model, hence proving the scheme is lightweight. The validation test shows the scheme has a high accuracy at 95.24%. It shows a precision of 100% in detecting WiFi and microwave oven interference while a 90% precision in detecting bluetooth interference.
Lightweight IoT middleware for rapid application development A. Karim Mohamed Ibrahim; Rozeha A. Rashid; A. Hadi Fikri A. Hamid; M. Adib Sarijari; Muhammad Ariff Baharudin
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 3: June 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i3.11793

Abstract

Sensors connected to the cloud services equipped with data analytics has created a plethora of new type of applications ranging from personal to an industrial level forming to what is known today as Internet of Things (IoT). IoT-based system follows a pattern of data collection, data analytics, automation, and system improvement recommendations. However, most applications would have its own unique requirements in terms of the type of the smart devices, communication technologies as well as its application provisioning service. In order to enable an IoT-based system, various services are commercially available that provide services such as backend-as-a-service (BaaS) and software-as-a-service (SaaS) hosted in the cloud. This, in turn, raises the issues of security and privacy. However there is no plug-and-play IoT middleware framework that could be deployed out of the box for on-premise server. This paper aims at providing a lightweight IoT middleware that can be used to enable IoT applications owned by the individuals or organizations that effectively securing the data on-premise or in remote server. Specifically, the middleware with a standardized application programming interface (API) that could adapt to the application requirements through high level abstraction and interacts with the application service provider is proposed. Each API endpoint would be secured using Access Control List (ACL) and easily integratable with any other modules to ensure the scalability of the system as well as easing system deployment. In addition, this middleware could be deployed in a distributed manner and coordinate among themselves to fulfil the application requirements. A middleware is presented in this paper with GET and POST requests that are lightweight in size with a footprint of less than 1 KB and a round trip time of less than 1 second to facilitate rapid application development by individuals or organizations for securing IoT resources.
A hybrid predictive technique for lossless image compression N. A. N. Azman; Samura Ali; Rozeha A. Rashid; Faiz Asraf Saparudin; Mohd Adib Sarijari
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (544.942 KB) | DOI: 10.11591/eei.v8i4.1612

Abstract

Compression of images is of great interest in applications where efficiency with respect to data storage or transmission bandwidth is sought.The rapid growth of social media and digital networks have given rise to huge amount of image data being accessed and exchanged daily. However, the larger the image size, the longer it takes to transmit and archive. In other words, high quality images require huge amount of transmission bandwidth and storage space. Suitable image compression can help in reducing the image size and improving transmission speed. Lossless image compression is especially crucial in fields such as remote sensing healthcare network, security and military applications as the quality of images needs to be maintained to avoid any errors during analysis or diagnosis. In this paper, a hybrid prediction lossless image compression algorithm is proposed to address these issues. The algorithm is achieved by combining predictive Differential Pulse Code Modulation (DPCM) and Integer Wavelet Transform (IWT). Entropy and compression ratio calculation are used to analyze the performance of the designed coding. The analysis shows that the best hybrid predictive algorithm is the sequence of DPCM-IWT-Huffman which has bits sizes reduced by 36%, 48%, 34% and 13% for tested images of Lena, Cameraman, Pepper and Baboon, respectively.
A hybrid predictive technique for lossless image compression N. A. N. Azman; Samura Ali; Rozeha A. Rashid; Faiz Asraf Saparudin; Mohd Adib Sarijari
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (544.942 KB) | DOI: 10.11591/eei.v8i4.1612

Abstract

Compression of images is of great interest in applications where efficiency with respect to data storage or transmission bandwidth is sought.The rapid growth of social media and digital networks have given rise to huge amount of image data being accessed and exchanged daily. However, the larger the image size, the longer it takes to transmit and archive. In other words, high quality images require huge amount of transmission bandwidth and storage space. Suitable image compression can help in reducing the image size and improving transmission speed. Lossless image compression is especially crucial in fields such as remote sensing healthcare network, security and military applications as the quality of images needs to be maintained to avoid any errors during analysis or diagnosis. In this paper, a hybrid prediction lossless image compression algorithm is proposed to address these issues. The algorithm is achieved by combining predictive Differential Pulse Code Modulation (DPCM) and Integer Wavelet Transform (IWT). Entropy and compression ratio calculation are used to analyze the performance of the designed coding. The analysis shows that the best hybrid predictive algorithm is the sequence of DPCM-IWT-Huffman which has bits sizes reduced by 36%, 48%, 34% and 13% for tested images of Lena, Cameraman, Pepper and Baboon, respectively.
A hybrid predictive technique for lossless image compression N. A. N. Azman; Samura Ali; Rozeha A. Rashid; Faiz Asraf Saparudin; Mohd Adib Sarijari
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (544.942 KB) | DOI: 10.11591/eei.v8i4.1612

Abstract

Compression of images is of great interest in applications where efficiency with respect to data storage or transmission bandwidth is sought.The rapid growth of social media and digital networks have given rise to huge amount of image data being accessed and exchanged daily. However, the larger the image size, the longer it takes to transmit and archive. In other words, high quality images require huge amount of transmission bandwidth and storage space. Suitable image compression can help in reducing the image size and improving transmission speed. Lossless image compression is especially crucial in fields such as remote sensing healthcare network, security and military applications as the quality of images needs to be maintained to avoid any errors during analysis or diagnosis. In this paper, a hybrid prediction lossless image compression algorithm is proposed to address these issues. The algorithm is achieved by combining predictive Differential Pulse Code Modulation (DPCM) and Integer Wavelet Transform (IWT). Entropy and compression ratio calculation are used to analyze the performance of the designed coding. The analysis shows that the best hybrid predictive algorithm is the sequence of DPCM-IWT-Huffman which has bits sizes reduced by 36%, 48%, 34% and 13% for tested images of Lena, Cameraman, Pepper and Baboon, respectively.
Interference Temperature Measurements and Spectrum Occupancy Evaluation in the Context of Cognitive Radio Paulson N. Eberechukwu; Dauda S. Umar; Alias Mohd; Kamaludin M. Y.; M. Adib bin Sarijari; Rozeha A. Rashid
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 3: June 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v10.i3.pp1007-1012

Abstract

This paper presents a refined radio spectrum measurement platform specifically designed for spectrum occupancy surveys in the context of Cognitive radio. Cognitive radio permits the opportunistic usage of licensed bands by unlicensed users without causing harmful interference to the licensed user. In this work, a study based on the measurement of the 800 MHz to 2.4 GHz frequency band at two different locations inside Universiti Teknologi Malaysia (UTM), Johor Bahru campus, Malaysia is presented. Two Tektronix RSA306B spectrum analyzer are set up to conduct simultaneous measurements at different locations for a 24 hours period. The analysis conducted in this work is based on the real spectrum data acquired from environment in the experimental set up. Busy and idle channels were identified. The channels subject to adjacent-channel interference were also identified, and the impact of the detection threshold used to detect channel activities was also discussed. The consistency of the observed channel occupation over a range of thresholds and a sudden drop has good characteristics in determining an appropriate threshold needed in order to avoid interference.