Adetokunbo Arogbonlo

Adetokunbo Arogbonlo

Auto-generated profile, based on publicly available information

Adetokunbo Arogbonlo

Deakin University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
8 September 2023 in Journal of Advanced Transportation
Verified
Journal Article
Open access
PDF file
ASArian Shajari
Arian Shajari
Houshyar AsadiHoushyar Asadi
Houshyar Asadi
Sébastien GlaserSébastien Glaser
Sébastien Glaser
AAAdetokunbo Arogbonlo
Adetokunbo Arogbonlo
SMShady Mohamed
Shady Mohamed
SNSaeid Nahavandi
Saeid Nahavandi
For decades, road crashes have caused many deaths and injuries and generally have had a severe social and economic impact on societies. According to studies, driver distraction has led to an increase in driving-related risks. In recent years, there have been more distracting factors that commonly affect drivers, highlighting the need for a resolution. Therefore, as technology is becoming more advanced, there is an opportunity to minimize these risks, for which driver distraction detection would be required. As there are a variety of distractions that might affect drivers and their performance, there are many studies focusing on this topic. To better understand the field of driver distraction detection, this paper has reviewed the existing studies in this field. For this purpose, different variables of the existing methodologies and experimental setups are identified and explained. Also, the results of these experiments and the impacts of different distraction factors on drivers’ physiological responses, visual signals, or their performances are categorized and described. Furthermore, this study discusses the factors of the existing methodologies and their results, along with pointing out the research gaps. The purpose of this study is to assist future research and investigation in this field, by creating a review that comprehensively covers different aspects of existing studies and discusses and assesses their methodologies and findings.

17 February 2025 in Computers
Verified
Journal Article
Open access
PDF file
MKMehshan Ahmed Khan
Mehshan Ahmed Khan
Houshyar AsadiHoushyar Asadi
Houshyar Asadi
Mohammad Reza Chalak QazaniMohammad Reza Chalak Qazani
Mohammad Reza Chalak Qazani
AAAdetokunbo Arogbonlo
Adetokunbo Arogbonlo
Siamak PedrammehrSiamak Pedrammehr
Siamak Pedrammehr
SNSaeid Nahavandi
Saeid Nahavandi
Functional near-infrared spectroscopy (fNIRS) is employed as a non-invasive method to monitor functional brain activation by capturing changes in the concentrations of oxygenated hemoglobin (HbO) and deoxygenated hemoglobin (HbR). Various machine learning classification techniques have been utilized to distinguish cognitive states. However, conventional machine learning methods, although simpler to implement, undergo a complex pre-processing phase before network training and demonstrate reduced accuracy due to inadequate data preprocessing. Additionally, previous research in cognitive load assessment using fNIRS has predominantly focused on differentiating between two levels of mental workload. These studies mainly aim to classify low and high levels of cognitive load or distinguish between easy and difficult tasks. To address these limitations associated with conventional methods, this paper conducts a comprehensive exploration of the impact of Long Short-Term Memory (LSTM) layers on the effectiveness of Convolutional Neural Networks (CNNs) within deep learning models. This is to address the issues related to spatial feature overfitting and the lack of temporal dependencies in CNNs discussed in the previous studies. By integrating LSTM layers, the model can capture temporal dependencies in the fNIRS data, allowing for a more comprehensive understanding of cognitive states. The primary objective is to assess how incorporating LSTM layers enhances the performance of CNNs. The experimental results presented in this paper demonstrate that the integration of LSTM layers with convolutional layers results in an increase in the accuracy of deep learning models from 97.40% to 97.92%.

8 July 2020 in IET Control Theory & Applications
Verified
Journal Article
Open access
PDF file
AAAdetokunbo Arogbonlo
Adetokunbo Arogbonlo
VHVan Thanh Huynh
Van Thanh Huynh
Aman Maung Than OoAman Maung Than Oo
Aman Maung Than Oo
MTMinh Hieu Trinh
Minh Hieu Trinh
This study addresses the problem of synthesising functional observers for positive time‐delay systems subjected to unknown inputs. A functional observer architecture for the problem is presented. The existence conditions of the observer and a linear programming problem characterising the existence conditions of such a functional observer are also established. An algorithm for designing the observer is presented. Finally, examples are given to showcase the effectiveness of the observer.

21 July 2025
Verified
Book Chapter
Closed access
PDF file
MKMehshan Ahmed Khan
Mehshan Ahmed Khan
Houshyar AsadiHoushyar Asadi
Houshyar Asadi
Mohammad Reza Chalak QazaniMohammad Reza Chalak Qazani
Mohammad Reza Chalak Qazani
AAAdetokunbo Arogbonlo
Adetokunbo Arogbonlo
SNSaeid Nahavandi
Saeid Nahavandi
Chee Peng LimChee Peng Lim
Chee Peng Lim

22 July 2024 in arXiv
Verified
Preprint
Open access
PDF file
MKMehshan Ahmed Khan
Mehshan Ahmed Khan
Houshyar AsadiHoushyar Asadi
Houshyar Asadi
Mohammad Reza Chalak QazaniMohammad Reza Chalak Qazani
Mohammad Reza Chalak Qazani
AAAdetokunbo Arogbonlo
Adetokunbo Arogbonlo
Siamak PedrammehrSiamak Pedrammehr
Siamak Pedrammehr
Chee Peng LimChee Peng Lim
Chee Peng Lim
Functional near-infrared spectroscopy (fNIRS) is employed as a non-invasive method to monitor functional brain activation by capturing changes in the concentrations of oxygenated haemoglobin (HbO) and deoxygenated haemo-globin (HbR). Various machine learning classification techniques have been utilized to distinguish cognitive states. However, conventional machine learning methods, although simpler to implement, undergo a complex pre-processing phase before network training and demonstrate reduced accuracy due to inadequate data preprocessing. Additionally, previous research in cog-nitive load assessment using fNIRS has predominantly focused on differ-sizeentiating between two levels of mental workload. These studies mainly aim to classify low and high levels of cognitive load or distinguish between easy and difficult tasks. To address these limitations associated with conven-tional methods, this paper conducts a comprehensive exploration of the im-pact of Long Short-Term Memory (LSTM) layers on the effectiveness of Convolutional Neural Networks (CNNs) within deep learning models. This is to address the issues related to spatial features overfitting and lack of tem-poral dependencies in CNN in the previous studies. By integrating LSTM layers, the model can capture temporal dependencies in the fNIRS data, al-lowing for a more comprehensive understanding of cognitive states. The primary objective is to assess how incorporating LSTM layers enhances the performance of CNNs. The experimental results presented in this paper demonstrate that the integration of LSTM layers with Convolutional layers results in an increase in the accuracy of deep learning models from 97.40% to 97.92%.