Nur Farhan Kahar
Thumbnail Image
Preferred name
Nur Farhan Kahar
Official Name
Nur Farhan, Kahar
Alternative Name
Kahar, Nur Farhan
Kahar, N. F.
Main Affiliation
Scopus Author ID
26633133000
Researcher ID
FEI-3508-2022

Research Output

Filters

3 1
2
Reset filters

Settings
Now showing 1 - 3 of 3
No Thumbnail Available
Publication

Use of natural language processing for the detection of hate speech on social media

2025-09 , Mehedi Hasan Shohan , Kazi Rifat Ahmed , Nur Farhan Kahar , Nusrat Jahan , Md. Maruf Hassan , Nadira Islam , R Badlishah Ahmad , Ong Bi Lynn , Naimah Yaakob

Our society’s communication patterns have fundamentally changed as a consequence of the emergence of social media platforms. One effect of these changes is a rise in unpleasant behaviours like making rude and derogatory comments online. Speaking harshly or disrespectfully to someone in person may be difficult. However, online abuse and posting of improper material are considered to be acceptable. Hate speech has the potential to hurt a person or a group of people. Inappropriate material must be identified, in order to be filtered or banned from the web. CNN is a type of deep machine-learning model that has been suggested for such identification, because it performs better than conventional techniques in resolving text categorization problems. Our goal investigates how hate speech may be detected using NLP. In addition, a recent technique has been used in this field to a dataset. This classifier is assigned in each tweet to one of the three Twitter dataset categories of hatred, foul language, or neither. This model’s performance has been assessed with accuracy. The Naïve Bayes, the Decision Tree, KNN, Linear Regression, and the Random Forest are five algorithms that have been used. Of these, Linear Regression provided the greatest accuracy of 94%. It should be noted that when looking at each class separately, many hateful tweets have been mislabelled. It is advisable to look at the outcomes and faults in much detail, in order to comprehend the misclassification. Our analysis shows a better outcome in detecting hateful speech in social media.

View
Thumbnail Image
Publication

Frequency Reconfigurable DRA using RF Switch Loaded Feedline for 5G NR Band n48, n77 and n78

2022-01-01 , Gunasekaran S.R. , Thennarasan Sabapathy , Muzammil Jusoh , R Badlishah Ahmad , Nur Farhan Kahar , Muhamad W.Z.A.W.

This paper presents a frequency reconfigurable DRA. The size of the antenna is approximately 50 mm by 40 mm, thus it can be considered a compact design. This antenna was designed using Rogers RO4003 substrate and the DRA material used was Eccostock HIK. To achieve frequency reconfiguration, the length of the antenna feedline was reconfigured by the means of RF switches. The proposed design consists of four configurations and all those conditions achieved reflection coefficient of less than -10 dB. The antenna also produced consistent gain for all configurations with average gain of 5 dBi. The switched frequencies from the proposed antenna can cover 5G New Radio Bands n48, n77 and n78.

View
Thumbnail Image
Publication

Gain Enhancement of Rectangular Dielectric Resonator Antenna Using Air Gap

2023-10-06 , Shanmuka Rooban Gunasekaran , Thennarasan Sabapathy , Muzammil Jusoh , R Badlishah Ahmad , Mohamed Nasrun Osman , Saidatul Norlyana Azemi , Nur Farhan Kahar , Wan Zuki Azman Wan Muhamad , Saravanan Nathan Lurudusamy

This paper presents a gain enhanced rectangular dielectric resonator antenna (DRA) using air gap. The air gap placed under the dielectric resonator antenna and above the ground plane. A gain of 6.605 dBi obtained from the DRA with air gap while gain of 5.956 dBi is achieved by DRA without air gap. The size of the antenna is approximately 50 mm by 40 mm, thus it can be considered a compact design. This antenna designed using Rogers RO4003 substrate and the DRA material is Eccostock HIK. All the design and simulation results are conducted using CST Studio Suite 2019 software. Based on the result, it shows that the antenna operates with reflection coefficient of less than -10 dB at the desired operating frequency range, centered at 3.5 GHz. The inclusion of air gap proved that it can enhance the gain value of the DRA.

View