Akinola Alimi Akinola

Mr. Akinola Alimi Akinola

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
16 July 2024 in IEEE Access
Verified
Journal Article
Open access
AAAkinola Alimi Akinola
Akinola Alimi Akinola
XLXiangfang Li
Xiangfang Li
RWRichard T Wilkins
Richard T Wilkins
POPamela H. Obiomon
Pamela H. Obiomon
LQLijun Qian
Lijun Qian
Image segmentation is a crucial task in computer vision. In this study, we propose a method based on inverse quantum Fourier transform (IQFT) and develop a robust IQFT-inspired algorithm for unsupervised image segmentation. The proposed method leverages the underlying mathematical mechanism of the IQFT to cluster the input image pixels automatically and efficiently into different segments. Specifically, by considering the correlation between the within-cluster mean sum of squared error (MSSE) and the probability of quantum measurements, the proposed robust algorithm significantly improves the segmentation performance. It is an unsupervised method with characteristics similar to k-means, i.e., the proposed method does not require training. Extensive evaluation of the proposed method has been carried out, showing that it outperforms the classical k-means on the PASCAL VOC 2012 segmentation benchmark by as much as 4.21%, the Flowers dataset by as much as 4.4%, and the xVIEW2 challenge dataset by as much as 11.1% in terms of Intersection-Over-Union (IoU). It is also demonstrated that the proposed method has comparable or mixed performance compared to recent more complex approaches. However, compared to approaches such as GrabCut, which require a measure of the user interaction, and deep learning-based methods, which require generative models and deep feature extraction algorithms, the proposed method does not require training or user involvement. This makes it a promising choice for applications that do not have access to data before deployment or have very limited training data.

12 December 2025 in IEEE Transactions on Antennas and Propagation
Verified
Journal Article
Closed access
OAOlaoluwa Ayodeji Adegboye
Olaoluwa Ayodeji Adegboye
AAAkinola Alimi Akinola
Akinola Alimi Akinola
XLXiangfang Li
Xiangfang Li
LQLijun Qian
Lijun Qian
This work presents a deep learning-based inverse design framework for rapid prototyping of fork antennas operating within the ultra-wideband (UWB) frequency. By integrating a pre-trained frozen forward model into the inverse training process, the proposed method with forward consistency loss ensures that predicted antenna geometries yield physically valid performance metrics. Three models were trained: Deep Neural Network (DNN), Long Short Term Memory (LSTM), and Echo State Network (ESN), to map performance targets to antenna dimensions. The results show that the models trained with forward consistency loss achieve a lower error in return loss, bandwidth, and frequency metrics. The proposed framework considering both forward loss and reverse loss outperforms inverse-only models, especially in complex high-frequency wideband scenarios. DNN and LSTM models demonstrated the best generalization at 3.5 GHz and 8 GHz, while all models significantly reduced the computational cost of antenna design compared to conventional simulation sweeps.

24 October 2025 in Frontiers in Communications and Networks
Verified
Journal Article
Open access
PDF file
ITIsrael Tommy
Israel Tommy
AAAkinola Alimi Akinola
Akinola Alimi Akinola
XLXiangfang Li
Xiangfang Li
LQLijun Qian
Lijun Qian
Introduction: Beam-level traffic forecasting plays a vital role in the optimization of 5G networks by enabling proactive resource allocation and congestion control. However, the task is complicated by inherent data sparsity and the presence of multi-scale temporal dynamics, making accurate predictions difficult to achieve using conventional models. Methods: To address these challenges, we propose a Gated Recurrent Unit (GRU)-based Multi-Task Learning (MTL) framework, enhanced by a weighted ensemble approach. We systematically evaluate the performance of six forecasting models—Linear Regression, DLinear, XGBoost, Echo State Network (ESN), Long Short-Term Memory (LSTM), and GRU-MTL—across three input sequence lengths (168-h, 24-h, and 8-h) using real-world beam-level data from the ITU AI for Good initiative. Results: Experimental findings reveal that the GRU-MTL model significantly outperforms traditional baselines, achieving a Mean Absolute Error (MAE) of 0.2136 on 168-h sequences compared to LSTM’s 0.3223. Long sequences (168-h) reduce MAE by 56% relative to short 8-h windows, effectively mitigating the effects of sparsity. Furthermore, an ensemble of top-performing models (MTL, XGBoost, and Linear Regression) yields additional gains, reducing MAE to 0.2105—a 1.45% improvement over MTL alone. Discussion: These results highlight the importance of long-term temporal context and model diversity for robust traffic prediction in sparse environments. The proposed framework offers practical guidelines: 168-h forecasting windows are optimal for weekly planning, and model ensembling enhances generalization across varying beam activity levels. This study contributes a scalable and accurate solution for spatio-temporal traffic forecasting in next-generation wireless networks.

11 January 2023 in arXiv
Verified
Preprint
Open access
PDF file
AAAkinola Alimi Akinola
Akinola Alimi Akinola
XLXiangfang Li
Xiangfang Li
RWRichard T Wilkins
Richard T Wilkins
POPamela Obiomon
Pamela Obiomon
LQLijun Qian
Lijun Qian
Image segmentation is a very popular and important task in computer vision. In this paper, inverse quantum Fourier transform (IQFT) for image segmentation has been explored and a novel IQFT-inspired algorithm is proposed and implemented by leveraging the underlying mathematical structure of the IQFT. Specifically, the proposed method takes advantage of the phase information of the pixels in the image by encoding the pixels' intensity into qubit relative phases and applying IQFT to classify the pixels into different segments automatically and efficiently. To the best of our knowledge, this is the first attempt of using IQFT for unsupervised image segmentation. The proposed method has low computational cost comparing to the deep learning-based methods and more importantly it does not require training, thus make it suitable for real-time applications. The performance of the proposed method is compared with K-means and Otsu-thresholding. The proposed method outperforms both of them on the PASCAL VOC 2012 segmentation benchmark and the xVIEW2 challenge dataset by as much as 50% in terms of mean Intersection-Over-Union (mIOU).

1 September 2026 in Telecom
Verified
Journal Article
Open access
PDF file
AAAkinola Alimi Akinola
Akinola Alimi Akinola
XLXiangfang Li
Xiangfang Li
LQLijun Qian
Lijun Qian
Reliable dynamic spectrum access in wide-area cognitive radio networks (CRNs) is challenged by sparse and erroneous spectrum-sensing measurements. This work formulates spatial-spectrum occupancy reconstruction as an image inpainting problem and proposes two cascaded deep learning models: a bidirectional long short-term memory-based image inpainting model (BiLSTM-IIM) and a binary diffusion-based image inpainting model (Diff-IIM). In both models, Stage 1 corrects sensing errors at observed locations, while Stage 2 reconstructs missing entries. The models are evaluated using simulations of a 2500m×2500m cognitive radio network with 50–200 secondary users, five primary users, and three spatial resolutions under representative wireless conditions. Both models generally outperform total variation and matrix completion baselines under sparse and noisy observations. Under moderate sensing errors, BiLSTM-IIM achieves accuracies of 92.91%, 93.66%, and 91.17% at the 10×10, 20×20, and 30×30 resolutions, respectively, while Diff-IIM achieves lower false-alarm rates with fewer parameters. Stage 1 reduces the sensing-error rate by approximately 58% for BiLSTM-IIM and 61% for Diff-IIM. These results support deep learning-based inpainting for wide-area spectrum occupancy reconstruction under the evaluated conditions.