Fares Alhaek

Dr. Fares Alhaek

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 February 2022 in Safety Science
Verified
Journal Article
Closed access
YHYahia Halabi
Yahia Halabi
浒 许浒 许
浒 许
DLDanbing Long
Danbing Long
YCYuhang Chen
Yuhang Chen
ZYZhixiang Yu
Zhixiang Yu
WAWael Alhaddad
Wael Alhaddad

15 January 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
Fares AlhaekFares Alhaek
Fares Alhaek
WLWeichao Liang
Weichao Liang
TRTaha Rajeh
Taha Rajeh
MJMuhammad Hafeez Javed
Muhammad Hafeez Javed
TLTianrui Li
Tianrui Li

28 December 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
TRTaha M. Rajeh
Taha M. Rajeh
TLTianrui Li
Tianrui Li
CLChongshou Li
Chongshou Li
MJMuhammad Hafeez Javed
Muhammad Hafeez Javed
ZLZhpeng Luo
Zhpeng Luo
Fares AlhaekFares Alhaek
Fares Alhaek

18 March 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
TRTaha Rajeh
Taha Rajeh
ZLZhipeng Luo
Zhipeng Luo
MJMuhammad Hafeez Javed
Muhammad Hafeez Javed
Fares AlhaekFares Alhaek
Fares Alhaek
TLTianrui Li
Tianrui Li
The rapid growth of Internet services dramatically drives the development of various intelligent technologies. As an important composition, modern ride-hailing platforms allow citizens to order taxis in a fast, simple, and secure manner. The key to developing a successful ride-hailing system largely depends on efficient fleet management that narrows the demand-supply gap. For this reason, many Deep Reinforcement Learning (DRL) frameworks are becoming increasingly popular for proactive taxi dispatching. However, existing approaches have very coarse formulations and solutions to the dispatching problem, which overly simplify the real situations. To this end, we propose a fine-grained DRL framework for effective taxi dispatching with tractable solutions. Our framework features three components 1) The basic model is a multi-agent DRL that optimizes the standard objectives (i.e., fulfilling the taxi orders). To reduce the status space and environment dynamics, we cluster regions based on their daily moving patterns and allow agents in the same cluster to learn cooperatively by sharing their policies, i.e., learning from like-pattern peers. 2) We further employ a recurrent neural network to forecast the demand and supply, which helps the agents make globally optimal decisions 3) Finally, we design a two-phase central dispatching strategy based on Maximum Network Flow to relocate taxis in fine granularity. We conduct extensive experiments in a realistic environment simulator using a real-world dataset, and the results demonstrate the superior performance of our new framework over existing approaches, promoting the average total order response rate by $2.67\%$ , taxi effort gain by $25.77\%$ , and decreasing the average number of repositions by $2.96\%$ .

18 December 2024 in Information Sciences
Verified
Journal Article
Closed access
Fares AlhaekFares Alhaek
Fares Alhaek
TLTianrui Li
Tianrui Li
TRTaha Rajeh
Taha Rajeh
MJMuhammad Hafeez Javed
Muhammad Hafeez Javed
WLWeichao Liang
Weichao Liang

17 November 2023
Verified
Conference Paper
Closed access
Fares AlhaekFares Alhaek
Fares Alhaek
WLWeichao Liang
Weichao Liang
TRTaha M. Rajeh
Taha M. Rajeh
MJMuhammad Hafeez Javed
Muhammad Hafeez Javed
TLTianrui Li
Tianrui Li
Automated driving systems and advanced driver assistance systems require accurate and reliable driver behavior recognition models to ensure safe and efficient operation. The complexity of background contents in real-world driving scenarios presents a significant challenge. Moreover, the distinction between different driving behaviors can be extremely subtle. Minor variations in body movements, gestures, or vehicle control, which are challenging to discern accurately, may indicate distinct behaviors. To address the above issues, this paper proposes a novel multi-model deep learning architecture (MMDLA) for driver behavior recognition by integrating multiple modalities, including RGB frames, depth information, and skeleton data, to provide a more comprehensive representation of driver behavior. The proposed model consists of two stages. In the first stage, we use local and global feature extraction to extract features from RGB and Depth frames. Additionally, we construct a graph from 3D skeleton data and feed it to a graph convolutional network to extract its features. In the second stage, we perform ensemble learning and fuse the diversity of multiple features together. Experiments on the Drive&Act dataset shows that our model achieves superior performance, outperforming existing models on both hierarchical and fine-grained activity recognition tasks.