Jabar Mahmood

Dr. Jabar Mahmood

Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 May 2023 in Sensors
Verified
Journal Article
Open access
PDF file
MBMICHAEL ABEBE BERWO
MICHAEL ABEBE BERWO
AKAsad Khan
Asad Khan
YFYong Fang
Yong Fang
HFHamza Fahim
Hamza Fahim
SJShumaila Javaid
Shumaila Javaid
SMSyam M.S.
Syam M.S.
Detecting and classifying vehicles as objects from images and videos is challenging in appearance-based representation, yet plays a significant role in the substantial real-time applications of Intelligent Transportation Systems (ITSs). The rapid development of Deep Learning (DL) has resulted in the computer-vision community demanding efficient, robust, and outstanding services to be built in various fields. This paper covers a wide range of vehicle detection and classification approaches and the application of these in estimating traffic density, real-time targets, toll management and other areas using DL architectures. Moreover, the paper also presents a detailed analysis of DL techniques, benchmark datasets, and preliminaries. A survey of some vital detection and classification applications, namely, vehicle detection and classification and performance, is conducted, with a detailed investigation of the challenges faced. The paper also addresses the promising technological advancements of the last few years.

30 June 2021 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
Jabar MahmoodJabar Mahmood
Jabar Mahmood
ZDZongtao Duan
Zongtao Duan
YYYun Yang
Yun Yang
QWQinglong Wang
Qinglong Wang
JAMEL NEBHENJAMEL NEBHEN
JAMEL NEBHEN
MBMuhammad Nasir Mumtaz Bhutta
Muhammad Nasir Mumtaz Bhutta
Recently, vehicular ad hoc networks (VANETs) got much popularity and are now being considered as integral parts of the automobile industry. As a subclass of MANETs, the VANETs are being used in the intelligent transport system (ITS) to support passengers, vehicles, and facilities like road protection, including misadventure warnings and driver succor, along with other infotainment services. The advantages and comforts of VANETs are obvious; however, with the continuous progression in autonomous automobile technologies, VANETs are facing numerous security challenges including DoS, Sybil, impersonation, replay, and related attacks. This paper discusses the characteristics and security issues including attacks and threats at different protocol layers of the VANETs architecture. Moreover, the paper also surveys different countermeasures.

5 April 2025 in Array
Verified
Journal Article
Open access
FNFareeha Naveed
Fareeha Naveed
AMAdven Masih
Adven Masih
Jabar MahmoodJabar Mahmood
Jabar Mahmood
MAMoeez Ahmed
Moeez Ahmed
AAAitizaz Ali
Aitizaz Ali
EAEbenezer Agbozo
Ebenezer Agbozo

22 November 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
EREphrem Retta
Ephrem Retta
RSRichard Sutcliffe
Richard Sutcliffe
Jabar MahmoodJabar Mahmood
Jabar Mahmood
MBMICHAEL ABEBE BERWO
MICHAEL ABEBE BERWO
EAeiad almekhlafi
eiad almekhlafi
JFJun Feng
Jun Feng
In a conventional speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language do not exist, data from other languages can be used instead. We experiment with cross-lingual and multilingual SER, working with Amharic, English, German, and Urdu. For Amharic, we use our own publicly available Amharic Speech Emotion Dataset (ASED). For English, German and Urdu, we use the existing RAVDESS, EMO-DB, and URDU datasets. We followed previous research in mapping labels for all of the datasets to just two classes: positive and negative. Thus, we can compare performance on different languages directly and combine languages for training and testing. In Experiment 1, monolingual SER trials were carried out using three classifiers, AlexNet, VGGE (a proposed variant of VGG), and ResNet50. The results, averaged for the three models, were very similar for ASED and RAVDESS, suggesting that Amharic and English SER are equally difficult. Similarly, German SER is more difficult, and Urdu SER is easier. In Experiment 2, we trained on one language and tested on another, in both directions for each of the following pairs: Amharic↔German, Amharic↔English, and Amharic↔Urdu. The results with Amharic as the target suggested that using English or German as the source gives the best result. In Experiment 3, we trained on several non-Amharic languages and then tested on Amharic. The best accuracy obtained was several percentage points greater than the best accuracy in Experiment 2, suggesting that a better result can be obtained when using two or three non-Amharic languages for training than when using just one non-Amharic language. Overall, the results suggest that cross-lingual and multilingual training can be an effective strategy for training an SER classifier when resources for a language are scarce.

1 January 2021 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
Jabar MahmoodJabar Mahmood
Jabar Mahmood
ZDZongtao Duan
Zongtao Duan
HXHeng Xue
Heng Xue
YYYun Yang
Yun Yang
MBMICHAEL ABEBE BERWO
MICHAEL ABEBE BERWO
AYAbd al Kader Ahmed Yassin
Abd al Kader Ahmed Yassin
The advancements in Vehicular Ad Hoc Networks (VANETs) require more intelligent security protocols that ultimately provide unbreakable security to vehicles and other components of VANETs. VANETs face various types of security pitfalls due to the openness characteristics of the VANET communication infrastructure. Researchers have recently proposed different mutual authentication schemes that address security and privacy issues in vehicle‐to‐vehicle (V2V) communication. However, some V2V security schemes suffer from inadequate design and are hard to implement practically. In addition, some schemes face vehicle traceability and lack anonymity. Hence, this paper’s primary goal is to enhance privacy preservation through mutual authentication and to achieve better security and performance. Therefore, this article first describes the vulnerabilities of a very recent authentication scheme presented by Vasudev et al. Our analysis proves that the design of Vasudev et al.’s scheme is incorrect, and resultantly, the scheme does not provide mutual authentication between a vehicle and vehicle server when multiple vehicles are registered with the vehicle sever. Furthermore, this paper proposes a secure message transmission scheme for V2V in VANETs. The proposed scheme fulfills the security and performance requirements of VANETs. The security analysis of the proposed scheme using formal BAN and informal discussion on security features confirm that the proposed scheme fulfills the security requirements, and the performance comparisons show that the proposed scheme copes with the lightweightness requirements of VANETs.

8 December 2025 in Scientific Reports
Verified
Journal Article
Open access
AMAdven Masih
Adven Masih
BABushra Afzal
Bushra Afzal
SFShamyla Firdoos
Shamyla Firdoos
Jabar MahmoodJabar Mahmood
Jabar Mahmood
AAAitizaz Ali
Aitizaz Ali
DBDaniel Musafiri Balungu
Daniel Musafiri Balungu
The rapid proliferation of AI-generated text from models such as ChatGPT-3.5 and ChatGPT-4 has raised critical challenges in verifying content authenticity and ensuring ethical use of language technologies. This study presents a comprehensive framework for distinguishing between human-written and GPT-generated text using a combination of machine learning, sequential deep learning, and transformer-based models. A balanced dataset of 20,000 samples was compiled, incorporating diverse linguistic and topical sources. Traditional algorithms and sequential architectures (LSTM, GRU, BiLSTM, BiGRU) were compared against advanced transformer models, including BERT, DistilBERT, ALBERT, and RoBERTa. Experimental findings revealed that RoBERTa achieved the highest performance (Accuracy = 96.1%), outperforming all baselines. Post-hoc temperature scaling (T = 1.476) improved calibration, while threshold tuning (t = 0.957) enhanced precision for high-stakes applications. McNemar’s test with Holm correction confirmed the statistical significance ( p < 0.05) of RoBERTa’s superiority. Efficiency analysis showed optimal trade-offs between accuracy and latency, and 20% pruning demonstrated sustainability potential. Furthermore, LIME and SHAP explainability analyses highlighted linguistic distinctions between AI-generated and human-authored text, and fine-grained error evaluation confirmed model robustness across text lengths. In conclusion, RoBERTa emerges as a reliable, interpretable, and computationally efficient model for detecting AI-generated content.