Olufade Falade Williams Onifade

Olufade Falade Williams Onifade

Auto-generated profile, based on publicly available information

Olufade Falade Williams Onifade

Department of Computer Science, University of Ibadan, Nigeria

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
25 November 2024 in Vietnam Journal of Computer Science
Verified
Journal Article
Open access
AIAyodeji Olusegun Ibitoye
Ayodeji Olusegun Ibitoye
OOOladosu O. Oladimeji
Oladosu O. Oladimeji
OOOlufade F. W. Onifade
Olufade F. W. Onifade
Mental health (MH) assessment and prediction have become critical areas of focus in healthcare, leveraging developments in natural language processing (NLP). Recent advancements in machine learning have facilitated the exploration of predictive models for MH based on user-generated comments that overlooked the integration of emotional attention mechanisms. The methods often struggle with contextual nuances and emotional subtleties, leading to suboptimal predictions. The prevailing challenge lies in accurately understanding the emotional context embedded within textual comments, which is crucial for effective prediction and intervention. In this research, we introduce a novel approach employing contextual emotional transformer-based models (CETM) for comment analysis in MH case prediction. CETM leverages state-of-the-art transformer architectures enhanced with contextual embedding layers and emotional attention mechanisms for MH case prediction. By incorporating contextual information and emotional cues, CETM captures the underlying emotional states and MH indicators expressed in user comments. Through extensive experimentation and evaluation, both Roberta and bidirectional encoder representations from transformers (BERT) models exhibited enhanced accuracy, precision, recall, and F1 scores compared to their counterparts lacking emotional attention. Notably, the Roberta model attained a greater accuracy of 94.5% when matched to BERT’s 87.6% when emotional attention was employed. Hence, by incorporating emotional context into the predictive model, we achieved significant improvements, which offers promising avenues for more precise and personalized MH interventions.

8 February 2023 in International Journal of Mathematical Sciences and Computing
Verified
Journal Article
Open access
PDF file
JAJoseph Damilola AKINYEMI
Joseph Damilola AKINYEMI
OOOlufade Falade Williams Onifade
Olufade Falade Williams Onifade
Among other factors affecting face recognition and verification, the aging of individuals is a particularly challenging one. Unlike other factors such as pose, expression, and illumination, aging is uncontrollable, personalized, and takes place throughout human life. Thus, while the effects of factors such as head pose, illumination, and facial expression on face recognition can be minimized by using images from controlled environments, the effect of aging cannot be so controlled. This work exploits the personalized nature of aging to reduce the effect of aging on face recognition so that an individual can be correctly recognized across his/her different age-separated face images. To achieve this, an individualized face pairing method was developed in this work to pair faces against entire sets of faces grouped by individuals then, similarity score vectors are obtained for both matching and non-matching image-individual pairs, and the vectors are then used for age-invariant face recognition. This model has the advantage of being able to capture all possible face matchings (intra-class and inter-class) within a face dataset without having to compute all possible image-to-image pairs. This reduces the computational demand of the model without compromising the impact of the ageing factor on the identity of the human face. The developed model was evaluated on the publicly available FG-NET dataset, two subsets of the CACD dataset, and a locally obtained FAGE dataset using leave-one-person (LOPO) cross-validation. The model achieved recognition accuracies of 97.01%, 99.89%, 99.92%, and 99.53% respectively. The developed model can be used to improve face recognition models by making them robust to agevariations in individuals in the dataset.

8 December 2023 in International Journal of Intelligent Systems and Applications
Verified
Journal Article
Open access
PDF file
AIAyodeji Olusegun Ibitoye
Ayodeji Olusegun Ibitoye
OOOlufade F.W. Onifade
Olufade F.W. Onifade
In computational study and automatic recognition of opinions in free texts, certain words in sentences are used to decide its sentiments. While analysing each customer’s opinion per time in churn management will be effective for personalised recommendations. Oftentimes, the opinion is not sufficient for contextualised content mining. While personalised recommendations are time consuming, it also does not provide complete picture of an overall sentiment in the business community of customers. To help businesses identify widespread issues affecting a large segment of their customers towards engendering patterns and trends of different customer churn behaviour, here, we developed a clustered contextualised conversation as opinions set for integration with Roberta Model. The developed churn behavioural opinion clusters disambiguated short messages while charactering contents collectively based on context beyond keyword-based sentiment matching for effective mining. Based on the predicted opinion threshold, customer churn category for group-based personalised decision support was generated, with matching concepts. The baseline RoBERTa model on the contextually clustered opinions, trained with a batch size of 16, a learning rate of 2e-5, over 8 epochs, using a maximum sequence length of 128 and standard hyperparameters, achieved an accuracy of 92%, Precision of 88%, Recall of 86% and F1 score of 84% over a test set of 30%.

12 February 2024
Verified
Book Chapter
Closed access
PDF file
COChristianah T. Oyewale
Christianah T. Oyewale
JAJoseph Damilola AKINYEMI
Joseph Damilola AKINYEMI
AIAyodeji Olusegun Ibitoye
Ayodeji Olusegun Ibitoye
OOOlufade F.W Onifade
Olufade F.W Onifade

8 October 2020 in International Journal of Image, Graphics and Signal Processing
Verified
Journal Article
Open access
PDF file
OOOlufade F. W. Onifade
Olufade F. W. Onifade
KOKabirat B. Olayemi
Kabirat B. Olayemi
FIFolasade Olubusola Isinkaye
Folasade Olubusola Isinkaye
Fingerprint biometric is popularly used for protecting digital devices and applications. They are better and more reliable for authentication in comparison to the usual security tokens or password, which make them to be at the forefront of identity management systems. Though, they have several security benefits, there are several weaknesses of the fingerprint biometric recognition system. The greatest challenge of the fingerprint biometric system is theft or leakage of the template information. Also, each individual has limited and unique fingerprint which is permanent throughout their lifespan, hence, the compromise of the fingerprint biometric will cause a lifetime threat to the security and privacy of such an individual. Security and privacy risk of fingerprint biometric have previously been studied in the context of cryptosystem and cancelable biometric generation. However, these approaches do not obviously address the issue of revocability, diversity and irreversibility of fingerprint features to guard against the wrong use or theft of fingerprint biometric information. In this paper, we proposed a model that harnesses the strength of Arnold transform and Bio-hashing on fingerprint biometric features to overcome the limitations commonly encountered in sole fingerprint biometric approaches. In the experimental analysis, the result of irreversibility showed 0% False Acceptance Rate (FAR), performance showed maximum of 0.2% FAR and maximum of 0.8% False Rejection Rate (FRR) at different threshold values. Also, the result of renewability/revocability at SMDKAB SMKADKB and SMKBDKA showed that the protection did not match each other. Therefore, the performance of the proposed model was notable and the techniques could be efficiently and reliably used to enforce protection on biometric templates in establishments/organizations so that their information and processes could be secured.

1 June 2022 in International Journal of Advances in Applied Sciences
Verified
Journal Article
Open access
PDF file
AIAyodeji Olusegun Ibitoye
Ayodeji Olusegun Ibitoye
OOOlufade F. W. Onifade
Olufade F. W. Onifade
Through the hype in digital marketing and the continuous increase in volume and velocity of opinions about an organization’s brands, churn prediction now requires advanced analytics in opinion mining for effective customer behavioral management beyond keywords sentiment analysis (SA). Earlier, by analyzing customers’ opinions using SA models, the extracted positive-negative polarity is used to classify customers as churners or non-churner. In those methods, the impact of word order, context, and the inherent semantics of the clustered opinion set were oftentimes overlooked. However, with the consistent creation of new words with new meanings mapped to existing words on the web, the research extended the fuzzy support vector model (FSVM) to show that the dependency distance between the headword, its dependent, and tail word can be weighted by using information content derived from a corpus to generate four-classed social opinion categories as a strongly positive, positive, negative, and strong negative. These opinion classes formed the basis for the churn category as a premium customer, Inertia customer potential churner, and churner in customer behavioral management. In performance evaluation, aside from engendering quadrupled churn class against the existing churn binary pattern, better accuracy, precision, and recall values were obtained when compared with existing SA works in support vector machine and fuzzy support vector machine (FSVM), respectively.