Abolaji Okikiade Ilori

Dr. Abolaji Okikiade Ilori


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
1 December 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
AOAkande Akinyinka Olukunle
Akande Akinyinka Olukunle
AKAkinde Olusola Kunle
Akinde Olusola Kunle
OJOdeyinka Oluwadara Joel
Odeyinka Oluwadara Joel
AIAbolaji Okikiade Ilori
Abolaji Okikiade Ilori
MAMatthew Olusegun Adigun
Matthew Olusegun Adigun
Sunday Adeola AJAGBESunday Adeola AJAGBE
Sunday Adeola AJAGBE
Pathloss is a key element that causes signal deterioration in the channel as the signal power reduces inversely with propagation distance, this deterioration experienced by the channel is majorly as a result of reflection, absorption, and scattering of the signal. This study however takes into consideration the radio path loss for precise base station (BS), frequency, and power adjustment prediction evaluated over a frequency of 2.3 GHz. With a distance range between 0.1 and 1.5 km for collection of data on the measured received signal strength (MRSS), five empirical models and a modified model were used to validate the measured data to determine their suitability for pathloss prediction at Federal University of Technology, Owerri (FUTO), Imo state, Nigeria. The results shows that the root mean square error (RMSE) for the Okumura-Hata, COST 231-Hata, Ericsson model, Lee, Stanford University Interim (SUI), ECC-33, and modified models are 14.33, 9.73, 25.79, 48.4, 33.76, and 8.31 dB respectively. Additionally, the Ericsson model provided 0.498 dB, the COST 231-Hata recorded 0.733 dB, and the modified model provided 0.453 dB for mean absolute percentage error (MAPE). Therefore, the improved model produces the best results, consequently, be deployed to approximately predict path loss for mobile radio coverage in Owerri, Nigeria.

26 September 2023
Verified
Book Chapter
Closed access
PDF file
Sunday Adeola AJAGBESunday Adeola AJAGBE
Sunday Adeola AJAGBE
YOYetunde J. Oguns
Yetunde J. Oguns
ATAnanth kumar Tamilarasan
Ananth kumar Tamilarasan
OOOlukayode Ayodele Oki
Olukayode Ayodele Oki
OAOluwakemi Abosede Adeola-Ajagbe
Oluwakemi Abosede Adeola-Ajagbe
OAOyetunde Adeoye Adeaga
Oyetunde Adeoye Adeaga

30 April 2024 in International Journal of Electrical Engineering and Applied Sciences (IJEEAS)
Verified
Journal Article
Open access
PDF file
OAOpeyemi Ajibola
Opeyemi Ajibola
OOOluwadara Odeyinka
Oluwadara Odeyinka
OAOlusola Akinde
Olusola Akinde
AAAkinyinka Akande
Akinyinka Akande
AIAbolaji Okikiade Ilori
Abolaji Okikiade Ilori
This paper is a performance survey on the residual energy of nodes in a wireless sensor network (WSN). Wireless sensor nodes are limited in application due to constraints in energy of nodes’ battery and addressing the problem of energy management is essential to lengthen the life of a deployed network of wireless sensors. In the method used, Sensor nodes were equally distributed on the complete border of the network field. An exclusive cluster, six hierarchical, and eighteen hierarchical clusters were formed based on even partition of the border of the network field. The choice of Cluster Head (CH) within each cluster formed was based on selection of a sensor node with minimal transmission distance to the Base Station. A comparison of the various hierarchical scenarios was simulated in MATLAB. The mean residue energies (MREs) after the network lifetime are 3%, 52%, and 35% of the initial node energy for single, six and eighteen hierarchical clusters respectively. The residual energies of sensor nodes above the recorded MREs were taken on a class interval of 50’s of the node identity (nid) and respective averages of residual energies of sensor nodes (AEr) of each selected class interval were evaluated. Based on the result, certain categories of sensor nodes at a section of the network field indicated that the battery energy of the affected nodes was not maximally utilized thereby leading to enormous residual energy. It was concluded that the residual energy of nodes in a WSN could be optimized to extend the lifetime.

3 December 2024
Verified
Book Chapter
Closed access
PDF file
OOOladeji Oluniyi Olanrele
Oladeji Oluniyi Olanrele
Sunday Adeola AJAGBESunday Adeola AJAGBE
Sunday Adeola AJAGBE
AIAbolaji Okikiade Ilori
Abolaji Okikiade Ilori
OAOluseyi Afolabi Adeyemi
Oluseyi Afolabi Adeyemi
The Industrial Internet of Things (IIoT) is a transformative technology with the potential to revolutionize the manufacturing industry. It connects sensors, devices, and machines to the Internet, creating an interconnected network that enables real-time data collection and transmission. This chapter provides an overview of IIoT architectures and their challenges across various sectors. Data acquired through the IIoT also facilitate a good and effective maintenance culture and assist in predicting and preventing failures of equipment, leading to substantial cost savings. Another benefit of the IIoT is its impact on product quality. By monitoring and controlling the manufacturing process, IIoT devices ensure that products meet desired specifications, resulting in fewer defects and improved overall product quality. The IIoT finds applications in diverse industries such as manufacturing, healthcare, logistics, and transportation. In the manufacturing industry, IIoT devices enable process monitoring and optimization, reducing costs and enhancing efficiency. In healthcare, the IIoT is utilized for patient health monitoring, automated drug delivery, and improved patient outcomes. In logistics and transportation, IIoT devices track shipments, monitor vehicle performance, and enhance safety. However, the vast amount of data generated by IIoT devices poses challenges. Computational intelligence techniques, including machine learning algorithms, can be employed to analyze these data, uncover patterns, and identify anomalies, enabling manufacturers to predict and prevent equipment failures. The chapter also addresses the challenges of implementing the IIoT, such as security and privacy concerns. The key takeaway of this chapter is that it offers insights into the implementation of the IIoT, the associated challenges, the vast amount of data provided by IIoT devices, and how it can optimize manufacturing processes and drive industrial advancements. <!----> <!----> <!----> <!---->

30 November 2023 in Research Square
Verified
Preprint
Open access
PDF file
KAKamoli Akinwale Amusa
Kamoli Akinwale Amusa
OIOlumayowa Ayodeji Idowu
Olumayowa Ayodeji Idowu
AIAbolaji Okikiade Ilori
Abolaji Okikiade Ilori
This paper is concerned with combinations of un-sharp masking, logarithmic transformation and adaptive histogram equalization techniques to arrive at a hybrid method for enhancement different types of medical image’ contrast. Motivation behind the hybridization is the need to have a contrast enhancement method that is not application specific and that can be deplored to several medical image enhancement. Four different types of medical images: X-ray, ultrasound, magnetic resonance and computer tomographic images are utilized in the evaluations of the proposed hybrid contrast enhancement method. As performance metrics, absolute mean brightness error, mean square error, peak signal to noise ratio and entropy are used. Comparative results both qualitative and quantitative, were conducted at the end of the research, and the proposed method out-perform other three (CLAHE, Fuzzy-based and Wavelet Transform-based) related selected methods in the field which used the same dataset in terms of testing accuracy. The enhancement quality of the proposed method was found to be satisfactory and can be used for any time of medical image, thus, the proposed hybrid technique produces better enhanced medical images from different medical image inputs.

1 January 2024 in ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)
Verified
Journal Article
Open access
PDF file
AIAbolaji Okikiade Ilori
Abolaji Okikiade Ilori
KAKamoli Akinwale Amusa
Kamoli Akinwale Amusa
EFEngr. Olumayowa Ayodeji Idowu, FNSE
Engr. Olumayowa Ayodeji Idowu, FNSE
This paper is concerned with combinations of un-sharp masking, logarithmic transformation, and adaptive histogram equalization techniques to arrive at a hybrid method for enhancement of different types of medical image's contrast. Motivation behind the hybridization is the need to have a contrast enhancement method that is not application-specific and that can be deployed to several medical image enhancements. Four different types of medical images: X-ray, ultrasound, magnetic resonance, and computer tomographic images are utilized in the evaluations of the proposed hybrid contrast enhancement method. As performance metrics, absolute mean brightness error, mean square error, peak signal to noise ratio, and entropy are used. Comparative results, both qualitative and quantitative, were conducted at the end of the research, and the proposed method outperformed the other three (CLAHE, fuzzy-based, and wavelet transform-based) related selected methods in the field that used the same dataset in terms of testing accuracy. The enhancement quality of the proposed method was found to be satisfactory and can be used for any time of medical image; thus, the proposed hybrid technique produces better enhanced medical images from different medical image inputs.