Kowovi Comivi Alowonou

Dr. Kowovi Comivi Alowonou

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
16 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
MSMikail Mohammed Salim
Mikail Mohammed Salim
Kowovi Comivi AlowonouKowovi Comivi Alowonou
Kowovi Comivi Alowonou
NTNurbek Sobir ugli Tojimurotov
Nurbek Sobir ugli Tojimurotov
HPHeejae Park
Heejae Park
JPJong Hyuk Park
Jong Hyuk Park
Resource constraints in the Industrial Internet of Things (IIoT) result in brute-force attacks, transforming them into a botnet to launch Distributed Denial of Service Attacks. The delayed detection of botnet formation presents challenges in controlling the spread of malicious scripts in other devices and increases the probability of a high-volume cyberattack. In this paper, we propose a secure Blockchain-enabled Digital Framework for the early detection of Bot formation in a Smart Factory environment. A Digital Twin (DT) is designed for a group of devices on the edge layer to collect device data and inspect packet headers using Deep Learning for connections with external unique IP addresses with open connections. Data are synchronized between the DT and a Packet Auditor (PA) for detecting corrupt device data transmission. Smart Contracts authenticate the DT and PA, ensuring malicious nodes do not participate in data synchronization. Botnet spread is prevented using DT certificate revocation. A comparative analysis of the proposed framework with existing studies demonstrates that the synchronization of data between the DT and PA ensures data integrity for the Botnet detection model training. Data privacy is maintained by inspecting only Packet headers, thereby not requiring the decryption of encrypted data.

8 December 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
ODOluwaseun E. Duntoye
Oluwaseun E. Duntoye
Kowovi Comivi AlowonouKowovi Comivi Alowonou
Kowovi Comivi Alowonou
DKDohoon Kwon
Dohoon Kwon
Accurate forecasting of wind power is essential for maintaining the stability and efficiency of power networks as renewable energy sources become more integrated. This study proposes a multilevel spatial-temporal graph convolution network (MLAGCN) for wind power forecasting. The framework combines a multilevel adaptive graph convolution (MLAGC) and a lightweight temporal transformer (LWTT) to jointly model complex spatial-temporal relationships in wind power data. MLAGC is constructed using three adaptive graphs: a local-aware graph, a global-aware graph, and a structure-aware graph. These components form a flexible graph structure that effectively represents dynamic spatial interactions while LWTT learns short- and long-term sequential patterns. Experiments on real wind farm datasets demonstrated that the proposed model outperforms existing baselines. The model achieved an improved prediction accuracy and generalization, as indicated by a lower score of 43.44, mean absolute error (38.83), root mean square error (48.05) and a forecast loss of 0.22. These results demonstrates the effectiveness of temporal modeling and multilevel attention-based adaptive graph learning for high-resolution wind power forecasting.

29 December 2025 in Energies
Verified
Journal Article
Open access
PDF file
Oluwaseun Emmanuel DuntoyeOluwaseun Emmanuel Duntoye
Oluwaseun Emmanuel Duntoye
Kowovi Comivi AlowonouKowovi Comivi Alowonou
Kowovi Comivi Alowonou
DKDohoon Kwon
Dohoon Kwon
Accurate forecasting of wind power is essential for maintaining the stability and efficiency of power networks as renewable energy sources become more integrated. This study proposes a multi-level spatial–temporal graph convolution network (MLAGCN) that combines a multi-level adaptive graph convolution (MLAGC) and a temporal transformer module (TTM) for wind power forecasting. Specifically, MLAGC first extracts spatial representations for each turbine at every time step by dynamically modeling local, global, and structural interactions. These spatial embeddings are then organized as temporal sequences and fed into TTM, which captures both short-term fluctuations and long-term temporal dependencies via self-attention. MLAGC is constructed using three adaptive graphs: a local-aware graph, a global-aware graph, and a structure-aware graph. These components form a flexible graph structure that effectively represents dynamic spatial interactions, while TTM learns short- and long-term sequential patterns. Experiments on real wind farm datasets demonstrated that the proposed model outperforms existing baselines. The model achieved improved prediction accuracy and generalization, as indicated by a lower composite score (defined as the average of MAE and RMSE) of 43.44, and a forecast loss of 0.22. These results demonstrate the effectiveness of temporal modeling and multi-level attention-based adaptive graph learning for high-resolution wind power forecasting.